https://arxiv.org/api/NVrhZcQLXeZTw6zq4b5b9bjiNlU 2026-09-27T19:43:07Z 120 361 0 http://arxiv.org/abs/2609.04550v1 2026-09-03T23:13:56Z

Video-language benchmarks are usually constructed by the dataset authors without published reliability statistics, leaving the noise floor of the construct unknown. We argue that multimodal benchmarking benefits from methods taken from research communities that have already invested in strategies to ensure reliability. We illustrate the case with the Classroom Observation Protocol for Undergraduate STEM (COPUS): a 24-code multi-label observation instrument with a decade of peer-reviewed reliability literature. We recast COPUS as a video benchmark for multimodal foundation models, where it provides a dense set of structured labels (a 24-dimensional binary vector every 2 minutes across a 50-90 minute lecture), an externally validated vocabulary, and established literature that provides a per-code reliability target based on human evaluators. Annotations in our evaluation corpus are produced by a 5-person human-evaluator panel whose consensus matrix is our reference. We propose VISTA, a baseline that runs MiniCPM-V-4.5 over a dense sliding window, refines its per-window outputs with a lightweight multi-layer perceptron (MLP) head trained on top of the frozen backbone, and max-pools the resulting predictions onto the 2-minute COPUS grid. On three held-out chemistry lectures, VISTA reaches 80.1% restricted macro accuracy versus 74.9% for the zero-shot variant, with the largest residual errors on visually similar instructor codes and on rare audio-dependent codes. We characterize three systematic failure modes (audio-partial observability, fine-grained group-work discrimination, long-tail recall) and release the benchmark tooling, prompts and baseline code at https://github.com/ajfranck/VISTA.

2026-09-03T23:13:56Z DataMFM Workshop @ Computer Vision & Pattern Recognition (CVPR) 2026 Andrew Franck Brendan Ng Ben Fitzgerald Zane Derrod Chris Cianci Chris Craney http://arxiv.org/abs/2608.14179v1 2026-08-14T10:49:39Z

Large language models (LLMs) have shown remarkable reasoning and generative capabilities, motivating their use as universal reasoning engines for perception. While modern approaches such as vision-language models (VLMs) have attempted to incorporate reasoning capabilities into visual sensing, the integration of LLMs with the millimeter-wave (mmWave) modality-despite its unique advantages under low light and occlusion-remains largely unexplored. The principal bottlenecks stem from the scarcity of radar language pairs, severe cross-dataset heterogeneity, and the absence of a foundational mmWave encoder. We address this gap through a minimal textualization interface that serializes each mmWave point cloud into concise natural language, allowing off-the-shelf LLMs to operate in a question answering (QA) setting. Building on this, we present mmWave-QA, the first benchmark for language-conditioned mmWave human perception. mmWave-QA aggregates heterogeneous public mmWave datasets and harmonizes them via calibration-aware preprocessing and global taxonomy alignment, while providing natural language QA. Spanning six scenarios and five QA tasks, the benchmark enables standardized evaluation across diverse mmWave hardware and experimental conditions, establishing a foundation for scalable research on mmWave-LLM integration. We further evaluate and analyze LLMs on our mmWave-QA, highlighting their zero-shot reasoning potential for radar perception, as well as their robustness under visual degradation.

2026-08-14T10:49:39Z Accepted to CVPR 2026 Findings Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026 Jeongwan Shin Jaehyeon Kim Donguk Ko Jaeho Choi http://arxiv.org/abs/2608.11367v1 2026-08-11T19:23:48Z

Estimating human gaze targets from images in-the-wild is an important and formidable task. Existing approaches primarily employ brittle, multi-stage pipelines that require explicit inputs, like head bounding boxes and human pose, in order to identify the subject of gaze analysis. As a result, detection errors can cascade and lead to failure. Moreover, these prior works lack the flexibility of specifying the gaze analysis task via natural language prompting, an approach which has been shown to have significant benefits in convenience and scalability for other image analysis tasks. To overcome these limitations, we introduce the Promptable Gaze Target Estimation (PGE) task, a new end-to-end, concept-driven paradigm for gaze analysis. PGE conditions gaze prediction on flexible user text or visual prompts (e.g., "the boy in the red shirt" or "person in point [0.52, 0.48]") to identify a specific subject for gaze analysis. This approach integrates subject localization with gaze estimation, and eliminates the rigid dependency on intermediate analysis stages. We develop a scalable data engine to generate Gaze-Co (Gaze Estimation with Concepts), a dataset and benchmark of 120K high-quality, prompt-annotated image pairs. We also propose GazeAnywhere, the first model designed for PGE. GazeAnywhere uses a transformer-based detector to fuse features from frozen encoders and simultaneously solves subject localization, in/out-of-frame presence, and gaze target heatmap estimation. GazeAnywhere achieves state-of-the-art performance on multiple PGE benchmarks, setting a strong baseline for this new problem even on a difficult out-of-domain, real-world clinical dataset. GazeAnywhere is open-sourced in github.com/IrohXu/GazeAnywhere.

2026-08-11T19:23:48Z CVPR 2026 Code and Benchmark are aviliable at https://github.com/IrohXu/GazeAnywhere and https://huggingface.co/datasets/IrohXu/Gaze-Co-Benchmark Xu Cao Houze Yang Vipin Gunda Zhongyi Zhou Tianyu Xu Adarsh Kowdle Inki Kim James M. Rehg http://arxiv.org/abs/2607.16351v1 2026-07-17T06:20:20Z

Publicly shareable construction-video benchmarks remain scarce, especially for safety-critical hazards that are rare, dangerous to stage, and difficult to release. We study worker under suspended load, a relational hazard that depends on worker-load geometry and temporal persistence rather than object detection alone. We introduce SynthSite, a focused synthetic video benchmark of 55 clips spanning varied load configurations, viewpoints, clutter, occlusions, and surveillance conditions, together with a privacy-aware hybrid generation workflow that supports both publicly shareable benchmark creation and privacy-constrained synthetic video generation. We then ask whether worker appearance can be suppressed without undermining downstream hazard recognition. Under five whole-body privacy conditions, we evaluate worker and load retention, localization stability, and clip-level hazard recognition. We find that structure-preserving obfuscations retain substantially more downstream utility than appearance-smoothing baselines, and that preserving a raw visual reference alone does not guarantee the strongest agreement with human hazard labels. These findings suggest that privacy evaluation for construction safety analytics should assess not only appearance suppression, but also preservation of the geometric cues required for hazard reasoning. Our dataset and code are available at https://huggingface.co/datasets/govtech/SynthSite .

2026-07-17T06:20:20Z Accepted at the 3rd Workshop on Synthetic Data for Computer Vision (SynData4CV), CVPR 2026. OpenReview: https://openreview.net/forum?id=dMfhFmDWsg . Dataset and code: https://huggingface.co/datasets/govtech/SynthSite Anshu Singh Alejandro Seif http://arxiv.org/abs/2607.16330v1 2026-07-15T18:22:21Z

This paper investigates whether multimodal LLMs can evaluate local brushstroke quality in calligraphy and generate educationally useful natural language feedback. We construct an evaluation framework in which three multimodal LLMs (GPT-4o, Claude Sonnet 4, and Gemini 2.5 Flash) assess before-after image pairs of calligraphic works using a five-point ordinal scale, and compare their outputs against scores assigned by three expert calligraphers. We additionally examine a Retrieval-Augmented Generation (RAG) variant of Claude as a preliminary condition. Results show that all models achieve useful levels of absolute score accuracy (MAE), with GPT-4o performing best (MAE = 0.885). However, none of the models produce statistically significant overall rank correlations with human experts (Kendall's tau). Vocabulary analysis of generated rationales reveals characteristic evaluative biases in each model, and RAG is shown to improve rank correlation while worsening absolute accuracy, constituting an important negative result for text-based rule injection.

2026-07-15T18:22:21Z 6 pages, 8 figures. Accepted to the SAUAFG Workshop at CVPR 2026 Mio Mitamura Hirokatsu Kataoka http://arxiv.org/abs/2607.07880v1 2026-07-08T19:30:44Z

Synthesizing realistic full-body human interactions with articulated objects is a fundamental challenge for embodied AI and graphics, with applications in robotics training and virtual agents. Existing models remain limited: some focus on simple activities with static objects, while others restrict attention to hand-only manipulation. This leaves open the problem of generating coordinated full-body motion that approaches, manipulates, and moves articulated objects in a realistic and generalizable way. The key difficulty lies in reasoning jointly about locomotion, fine-grained contact, and object articulation. Models must capture subtle hand-object correspondences that transfer across object geometries, while also producing seamless transitions from navigation to manipulation. At the same time, the scarcity of large-scale paired motion-scene data makes it difficult to generalize across diverse object positions and shapes. We introduce a text-conditioned diffusion model that addresses these challenges through three core ideas: an object-centric representation that unifies hand-object contact with object surfaces, a mixed-domain training strategy that balances locomotion and interaction, and a contact-based augmentation scheme that expands training diversity. Through experiments, our method demonstrated strong generalization to unseen object configurations, surpassing current state-of-the-art methods.

2026-07-08T19:30:44Z 12 pages, 6 figures, 3 tables. Accepted at the Third Workshop on Human Motion Generation (HuMoGen), CVPR 2026 Xiaohan Zhang Sebastian Starke Alexander Winkler Federica Bogo Samir Aroudj Yuting Ye http://arxiv.org/abs/2607.07693v1 2026-07-08T17:49:49Z

Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for aligning generative models with human preferences. However, applying RLHF to diffusion models remains highly feedback inefficient, as existing approaches typically require large amounts of human or reward model evaluations. This limitation reduces the practicality of diffusion RLHF in realworld settings where feedback is the primary bottleneck. In this paper, we propose two complementary strategies that substantially improve the feedback efficiency of diffusion RLHF while preserving generalization to unseen prompts. Our key observation is that reward information in diffusion trajectories is unevenly distributed: not all denoising timesteps or trajectories contribute equally to learning from a reward signal. By emphasizing informative timesteps and trajectories during optimization, we obtain more effective gradient updates. First, we introduce a per-timestep weighting scheme that reweights denoising steps during policy optimization. We theoretically connect this weighting to the optimal convergence properties of proximal policy optimization (PPO) and approximate the resulting weighting trend empirically. Second, we introduce a replay mechanism that prioritizes informative trajectories, enabling the model to reuse past samples instead of repeatedly querying new rewards. Together, these strategies significantly improve the feedback efficiency of diffusion RLHF. Under identical hyperparameter settings, our approach achieves up to a 6$\times$ improvement in sample efficiency compared to widely used diffusion RLHF baselines.

2026-07-08T17:49:49Z 19 pages, 18 figures, 4 tables. Submission under review. A shorter, non-archival 4-page abstract version of this work was accepted to CVPR 2026 Workshops (GCV, CVEU) Eric Zhu Abhinav Shrivastava Soumik Mukhopadhyay http://arxiv.org/abs/2606.30101v1 2026-06-29T10:37:21Z

Existing robot policies based on learned visual embeddings lack explicit structure and are sensitive to visual distractions. Thus, the representations that drive their behaviour are often opaque, making their decision-making process difficult to interpret. To address this, we introduce Structured Image Representations (SIR), a method that leverages Scene Graphs (SGs) as an intermediate representation for robot policy learning. Our approach first constructs a fully connected graph, using image-derived features as initial node representations. Then, a module learns to sparsify this graph end-to-end, creating a task-relevant sub-graph that is passed to the action generation model. This process makes our model intrinsically explainable. Evaluations on RoboCasa show that our sparse graph policies outperform image-based baselines on average with 19.5% vs 14.81% success rate. Most importantly, we show that the learned sparse graphs are a powerful tool for model analysis. By analysing when the model's sub-graph deviates from human expectation, such as by including distractor nodes or omitting key objects, we successfully uncover dataset biases, including spurious correlations and positional biases. https://github.com/intuitive-robots/SIR_Model

2026-06-29T10:37:21Z Published at CVPR 2026 In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2026. S. 42484-42493 Paul Mattes Jan Schwab Jens Bosch Nils Blank Maximilian Xiling Li Minh-Trung Tang Moritz Haberland Rudolf Lioutikov http://arxiv.org/abs/2606.28604v1 2026-06-26T20:52:54Z

Capturing full-body human motion with object interactions is crucial for AR/VR and robotics applications, yet it remains challenging for conventional vision-based methods due to occlusions and constrained capture volumes. Inertial measurement units (IMUs) offer a compelling alternative without line-of-sight requirements, but existing IMU-based motion capture assumes an isolated human and ignores object contacts and dynamics. To bridge this gap, we present IMU-HOI, a novel framework that jointly recovers full-body human pose and 6-DoF object trajectory from sparse IMUs on the body and object, explicitly modeling human-object interaction. Our approach first infers probabilistic hand-object contacts directly from IMU streams and uses them as a high-level signal to route between kinematic and inertial reasoning. These contact cues drive a three-stage fusion pipeline that refines human pose and root translation, and fuses hand-based forward kinematics with object-IMU integration for object motion, yielding coherent, drift-resilient trajectories for both human and object. Experiments on challenging human-object interaction scenarios demonstrate substantial accuracy gains over prior inertial motion capture methods. Moreover, IMU-HOI can be plugged into existing sparse-IMU mocap backbones with minimal changes, effectively extending the scope of purely inertial motion capture from isolated humans to full human-object interaction and joint motion estimation.

2026-06-26T20:52:54Z 10 pages, 5 figures. Accepted by CVPR 2026 Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2026, pp. 42901-42910 Lizhou Lin Songpengcheng Xia Zengyuan Lai Lan Sun Jiarui Yang Ling Pei http://arxiv.org/abs/2606.22363v1 2026-06-21T07:17:38Z

We introduce reference-free measures for evaluating the physical consistency of generated videos, combining relative and absolute approaches to assess fidelity. Although tools like WorldGym or WorldEval enable robotic simulation via video generation, physical fidelity gaps often prevent these environments from accurately reproducing real-world task success rates of VLA models. Unlike existing evaluation methods, which require costly human voting (Elo) or unavailable ground-truth references (FVD), our approach utilizes DROID-SLAM and SEA-RAFT to quantify physical inconsistencies, motivated by WorldScore. Videos filtered using our relative consistency assessment show an improvement in task success rates of over 8%, effectively narrowing the simulation-to-reality gap. Furthermore, our absolute assessment enables spatio-temporal localization, providing visualization of when and where physical artifacts occur.

2026-06-21T07:17:38Z Accepted to the 2nd 3D-LLM/VLA Workshop, CVPR 2026 Yun Oh Sukmin Yun http://arxiv.org/abs/2606.11148v1 2026-06-09T17:34:25Z

Virtual try-on aims to fit an in-shop clothing image onto a specific human body. An optimal virtual try-on method should provide diverse and flexible dressing options, accurately reflecting the varied wearing styles encountered in real-life scenarios, tailored to individual preferences and fashion aspirations. However, current methods predominantly perform a direct replacement of the original clothing with the target clothing, following the same dressing pattern. This limited control over clothing adaptation may result in fixed and monotonous try-on outputs. To delve into More Fashion Possibilities with Fine-Grained Adaptations in Virtual Try-On, we propose a novel virtual try-on method, termed MOFA-VTON, which allows adjustment for clothing adaptations in try-on results through simple sketches by users. Specifically, we first design a mask construction strategy that transforms user-drawn curve sketches into a dual-region mask, replacing the traditional clothing-agnostic mask and providing fine-grained layout guidance for the subsequent generation process. Further, we propose layout adjustment blocks that utilize the cross-attention mechanism to independently learn layout correspondences for upper and lower regions of the human body, refining the spatial arrangement of the two regions. With these implementations, our method enables flexible and fine-grained adaptations of target clothing, overcoming the constraints of a fixed layout. Extensive experiments on VITON-HD and DressCode datasets demonstrate that our proposed MOFA-VTON outperforms previous state-of-the-art methods and provides more fashion possibilities for virtual try-on.

2026-06-09T17:34:25Z Accepted to CVPR 2026 (Highlight) Xiaoyu Han Chenyang Wang Jing Wang Shunyuan Zheng Quanling Meng Shengping Zhang http://arxiv.org/abs/2606.10142v1 2026-06-08T20:17:49Z

Recent advances in 3D generation have led to substantial improvements in realism, controllability, and efficiency, yet the evaluation of 3D assets remains underexplored. Existing evaluation paradigms, including human evaluation, learned metrics, and vision-language models (VLMs) as judges, suffer from limitations in cost, scalability, resolution handling, or task-specific alignment. In this work, we focus on 3D mesh evaluation and introduce DB-3DME, the Dataset and Benchmark for 3D Mesh Evaluation. DB-3DME contains 2,619 synthetic 3D meshes paired with human ratings on Geometry and Prompt Adherence. Using this dataset, we systematically benchmark state-of-the-art VLMs and identify visual encoding of 3D representations as a key factor for human-aligned evaluation performance. Motivated by this finding, we fine-tune an open-weight VLM, Qwen-2.5-VL-7B, for 3D mesh evaluation by adapting the visual encoder while freezing the language model. The fine-tuned model substantially outperforms existing pre-trained VLMs across multiple evaluation dimensions, establishing a new benchmark for automatic 3D mesh evaluation. We publicly release the benchmark dataset on GitHub and Hugging Face to facilitate future research.

2026-06-08T20:17:49Z CVPR 2026 workshop paper. 10 pages, 3 figures, 6 tables. Dataset available at GitHub and Hugging Face Nanshan Jia Zhenyu Zhao Sui Huang Jingshen Wang Zeyu Zheng http://arxiv.org/abs/2606.08016v1 2026-06-06T07:11:08Z

Current image editing software often hinges on fixed filters or expert tuning, leaving a gap between amateur users' intent and outcomes. Creations by generative models may contain artifacts, implausible details, or stylistic drift away from photorealism and offer little insight into why an edit was made. We propose IEA, a conversational Image Editing Agent that learns to operate parameterized tools in an explicit, interpretable action space. IEA is trained via a three-stage multitask pipeline: (1) SFT on distilled expert edits, (2) GRPO with rewards for likeness improvement, tool usefulness, and intent summarization, and (3) large-scale synthetic fine-tuning to jointly master image editing, refinement, and user intent summarization. By manipulating 16 editing tools step by step, IEA produces transparent edit traces that can be inspected and debugged. In quantitative experiments, it attains a lower pixel distance on the edit task and a higher ROUGE-L on the summary task than strong baselines. In user studies, it ranks best among tool-calling methods for instruction following while surpassing generative methods in overall perceptual quality. Our results validate interpretable, tool-centric VLMs as a reliable path to human instruction-guided image retouching.

2026-06-06T07:11:08Z [CVPR 2026 Findings] Our data and code are released at https://github.com/OpenDFM/Image_Edit_Agent Zichen Zhu Yuheng Sun Mingxuan Zhu Wenjie Ma Situo Zhang Zhexiang Wang Ziyue Yang Danyang Zhang Kunyao Lan Zihan Zhao Dingye Liu Siqi Xiang Lu Chen Kai Yu http://arxiv.org/abs/2606.05399v2 2026-06-09T15:06:29Z

Existing feed-forward networks excel at predicting a single set of physical properties from visual appearance, but this point-estimate paradigm fundamentally fails to capture the real world's inherent physical ambiguity. We address this by reframing physics prediction as a task of learning a controllable, continuous distribution of material properties. We introduce UNIPIXIE, a framework trained to predict a continuous and parameterized path of physically plausible material properties from a single visual input. By learning a direct mapping along an object's softest-to-stiffest spectrum on our PIXIEMULTIVERSE dataset, UNIPIXIE allows for controllable generation of diverse, physically valid material fields via a single intuitive parameter. Crucially, UNIPIXIE introduces a novel unified architecture to produce simulation-ready parameters for diverse physics solvers, including continuum-based Material Point Method (MPM), reduced-order deformation based on Linear Blend Skinning (LBS), and anchor-based Spring-Mass systems, addressing a key portability issue in prior work. Experiments show our approach not only generates a rich variety of plausible dynamics but also reduces Young's Modulus prediction error by over 50% against the strongest deterministic baseline, bridging the gap between static point estimates and the continuous nature of physical reality. Project page: https://unipixie.github.io/

2026-06-03T20:08:23Z Published at CVPR 2026 as a Highlight. Project page: https://unipixie.github.io/ Qilin Huang Quynh Anh Huynh Long Le Chen Wang Chuhao Chen Ryan Lucas Eric Eaton Lingjie Liu http://arxiv.org/abs/2606.05359v1 2026-06-03T19:02:48Z

In this paper, we propose RePHO, a method to reconstruct physically plausible human-object interactions (HOI) from monocular videos. While existing kinematic-based approaches produce visually plausible motion, they often result in physically implausible artifacts such as interpenetration and object floating. To overcome these issues, we introduce a physics-guided reconstruction framework. We begin with a kinematic estimate and then refine it by training a policy with reinforcement learning (RL). This policy is optimized to reproduce the interaction in a physics simulator. Because kinematic estimates are typically noisy, naive RL training can fail. Therefore, we propose an adaptive sampling strategy with a dual self-updating mechanism that can identify the frames with the most informative and reliable kinematic reconstruction. Our process progressively improves reconstruction quality and yields physically consistent HOI sequences. We demonstrate our approach on two standard HOI benchmarks and achieve clear improvements in physical plausibility metrics over state-of-the-art methods. Project Page: https://dingbang777.github.io/RePHO/

2026-06-03T19:02:48Z CVPR 2026. Project Page: https://dingbang777.github.io/RePHO/ Dingbang Huang Etienne Vouga Qixing Huang Georgios Pavlakos http://arxiv.org/abs/2606.04925v1 2026-06-03T14:19:55Z

Video panoptic segmentation (VPS) aims to jointly detect, segment, and track all objects while partitioning the video into semantically consistent regions. We introduce the task setting of unsupervised VPS, omitting any human supervision. Existing unsupervised scene understanding works mainly focused on image segmentation tasks; the video domain remains underexplored. We propose VideoCUPS, the first unsupervised VPS approach. VideoCUPS generates temporally consistent panoptic video pseudo-labels from scene-centric videos by exploiting unsupervised depth, motion, and visual cues. Training on these pseudo-labels using a novel Video DropLoss yields an accurate, unsupervised VPS model. To benchmark progress, we introduce a comprehensive evaluation protocol and four competitive baselines, extending state-of-the-art unsupervised panoptic image and instance video segmentation models to VPS. VideoCUPS outperforms all baselines and demonstrates strong label-efficient learning. With VideoCUPS, our evaluation protocol, and baselines, we provide a strong foundation for future research on unsupervised VPS.

2026-06-03T14:19:55Z CVPR 2026. Oliver Hahn and Christoph Reich - both authors contributed equally. Code: https://github.com/visinf/cups/tree/main/videocups Project page: https://visinf.github.io/videocups/ Christoph Reich Oliver Hahn Nikita Araslanov Laura Leal-Taixé Christian Rupprecht Daniel Cremers Stefan Roth http://arxiv.org/abs/2606.03951v1 2026-06-02T17:39:07Z

Human experience in digital environments offers a vast, underexplored resource of authentic, untrimmed interactions that contain rich procedural knowledge. We introduce Demo2Tutorial, a framework that transforms this experience captured via screen recordings and interaction logs into structured, multimodal software tutorials for teaching both humans and agents. Demo2Tutorial first collects human experience via a dedicated recorder, then parses raw experience using a multimodal Action Parser to reconstruct perception, action, and intent. A Step Planner then abstracts these steps into hierarchical task graphs representing goals and steps. Finally, a Tutorial Composer transforms the parsed experience into structured, reusable image-text instructions. We evaluate the tutorial generation quality on a new benchmark derived from official software documentation. We further demonstrate that this distilled representation benefits (i) human learning, by automatically generating multimodal tutorials, and (ii) agent learning, by improving downstream GUI-agent planning and generalization. Experiments show Demo2Tutorial produces high-quality tutorials that surpass human-authored ones and significantly outperform baseline methods, while enabling both faster human task completion and improved GUI agent planning, demonstrating that structured tutorials distilled from human experience can serve as effective knowledge representations for advancing both human learning and agent capabilities. Code and data will be available at https://github.com/showlab/Demo2Tutorial.

2026-06-02T17:39:07Z Accepted by CVPR 2026 Zechen Bai Zhiheng Chen Yiqi Lin Kevin Qinghong Lin Difei Gao Xiangwu Guo Xin Wang Mike Zheng Shou http://arxiv.org/abs/2606.03577v1 2026-06-02T12:46:34Z

Wide-baseline matching (WBM) requires integrating geometric understanding, viewpoint changes, fine-grained perception, and occlusion reasoning, making it a challenging testbed for spatial reasoning in multimodal large language models (MLLMs) deployed in physical environments. However, current MLLMs lack systematic evaluation and training frameworks for these capabilities. We introduce ReasonMatch-Bench, a benchmark stratified by viewpoint displacement and matching granularity across indoor, outdoor, and object-centric scenarios, and show that current MLLMs still struggle with fine-grained wide-baseline correspondence: on a difficult 90-sample subset, human annotators achieve 84.0 F1, while the best existing baseline reaches 37.2. To bridge this gap, we build a scalable data-generation pipeline that automatically extracts wide-baseline view pairs from large-scale video-3D corpora, including RGB-D videos and SfM reconstructions, yielding diverse and verifiable supervision. We further propose Dynamic Correspondence Reinforcement Learning (DCRL), which combines Image-Level Viewpoint Progression and Point-Level Correspondence Curriculum to improve WBM training through verifiable rewards without explicit CoT supervision. Extensive experiments show that DCRL substantially improves ReasonMatch-Bench and transfers to related spatial benchmarks, while maintaining general visual understanding performance with modest gains on several benchmarks.

2026-06-02T12:46:34Z CVPR 2026. Project page: https://aim-uofa.github.io/reasonmatch/ Code: https://github.com/aim-uofa/ReasonMatch Hao Zhong Muzhi Zhu Shenyan Zeng Anzhou Li Cong Chen Hua Geng Duochao Shi Wentao Ye Tao Lin Hao Chen Chunhua Shen http://arxiv.org/abs/2606.03506v1 2026-06-02T11:24:31Z

Existing 3D avatar outfit transfer methods face distinct challenges: approaches that lift 2D edits to 3D often suffer from outfit or identity quality degradation, while those that separately model body and clothing layers are prone to intersection artifacts. We introduce AvatarMix, a compositional paradigm that bypasses these issues by directly composing the head and body from two high-fidelity Gaussian avatars. While this paradigm inherently preserves outfit quality and avoids intersections, it introduces challenges in creating a seamless join and maintaining appearance fidelity after body reshaping. To this end, we propose a two-tier refinement strategy: SeamFix, a localized diffusion module that refines hair and neck to ensure an artifact-free join, and an optional full-body refinement, FullbodyFix, that restores garment appearance when retargeting degrades the clothed body. Both operate on renders from an already 3D-consistent Gaussian avatar, which limits multi-view artifacts compared to 2D-to-3D lifting. To preserve the user's body identity, our mesh-based Gaussian representation enables the adaptation of a robust mesh retargeting technique, precisely reshaping the clothed body to the user's physique and robustly handling diverse body shapes. Extensive experiments demonstrate that our method achieves state-of-the-art results in outfit fidelity and identity preservation, providing a new perspective for realistic 3D outfit personalization. Project page: https://larsph.github.io/avatarmix/

2026-06-02T11:24:31Z CVPR 2026 Findings. 16 pages, including supplementary material Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026, pp. 425-435 Zhaorong Wang Yoshihiro Kanamori Yuki Endo http://arxiv.org/abs/2606.02996v1 2026-06-02T01:12:28Z

Inertial odometry (IO) using only Inertial Measurement Units (IMUs) provides a lightweight solution for human motion tracking in augmented reality (AR) and wearable devices. Recent learning-based IO methods have improved the generalizability of inertial localization through large-scale pretraining on human motion datasets. However, these approaches remain prone to drift and noise because they do not explicitly capture human motion dynamics, especially on daily activity datasets such as Nymeria. In this work, we propose to ground inertial odometry in human kinematics through a learned IMU-inferred pose prior, which promotes physically consistent motion constraints. We integrate this pose prior into existing IO architectures and reduce positional drift by up to 36% on the challenging Nymeria dataset, which is 5x larger than datasets used in prior work. We further improve long-term performance with a sensor-fusion framework that incorporates auxiliary signals from lightweight sensors already available on commercial AR glasses, including magnetometers, barometers, and secondary IMUs. With this fusion strategy, positional drift is reduced by up to 42%, improving robustness and generalization across diverse motion conditions. Together, our results introduce a new paradigm for inertial and lightweight odometry by unifying human motion kinematics with multimodal sensing, setting a new benchmark for accurate and robust camera-less human tracking. Our website is available at https://spice-lab.org/projects/MARIO/.

2026-06-02T01:12:28Z CVPR 2026 Findings Yiquan Li Taeyoung Yeon Chenfeng Gao Vasco Xu Xuanyou Liu Karan Ahuja http://arxiv.org/abs/2606.02573v1 2026-06-01T17:58:11Z

In this paper, we present HumanNOVA, a photorealistic, universal, and rapid model for generating 3D human avatars from a single RGB image. Achieving both photorealism and generalization is challenging due to the scarcity of diverse, high-quality 3D human data. To address this, we build a scalable data generation pipeline that follows two strategies. The first one is to leverage existing rigged assets and animate them with extensive poses from daily life. The second strategy is to utilize existing multi-camera captures of humans and employ fitting to generate more diverse views for training. These two strategies enable us to scale up to 100k assets, significantly enhancing both the quantity and the diversity of data for robust model training. In terms of the architecture, HumanNOVA adopts a feed-forward, token-conditioned avatar modeling framework that allows fast inference in less than one second and requires no test-time optimization. Given an input image and an estimated simplified human mesh (SMPL) without detailed geometry or appearance, the model first encodes both inputs into compact token representations. These tokens then act as conditioning signals and are fused through cross-attention to construct a triplane-based 3D avatar representation. Extensive experiments on multiple benchmarks demonstrate the superiority of our approach, both quantitatively and qualitatively, as well as its robustness under diverse input image conditions. Project page at https://HumanNOVA.github.io .

2026-06-01T17:58:11Z CVPR 2026 Highlight Hezhen Hu Wangbo Zhao Lanqing Guo Hanwen Jiang Jonathan C. Liu Zhiwen Fan Kai Wang Zhangyang Wang Georgios Pavlakos http://arxiv.org/abs/2606.02642v1 2026-05-31T14:00:37Z

Despite the success of audio-visual large-language models (LLMs), they can produce plausible but ungrounded outputs, termed hallucination. Existing benchmarks focus on environmental sounds (e.g., dog barking) to indicate event occurrence. In contrast, human speech carries fundamentally different, rich semantics and temporal structures, yet it remains unexplored whether current models can accurately align speech content with corresponding visual signals. In this work, we show that speech content can induce hallucinations in audio-visual LLMs. To systematically study this, we introduce SVHalluc, the first comprehensive benchmark for evaluating speech-vision hallucination in audio-visual LLMs. Our benchmark diagnoses speech-vision hallucinations from two critical and complementary aspects: semantic and temporal. Experimental results demonstrate that state-of-the-art open-source audio-visual LLMs struggle with aligning speech content with corresponding visual signals, with a near-random accuracy on multiple tasks. In contrast, Gemini 2.5 Pro significantly outperforms the open-source models. Our analysis suggests that their failures stem from limited ability in cross-modality understanding, despite strong performance in single-modality perception. Our work uncovers a new and fundamental limitation of current audio-visual LLMs and highlights the need for speech-grounded video comprehension. Project page: https://chenshuang-zhang.github.io/projects/svhalluc/.

2026-05-31T14:00:37Z Accepted at CVPR 2026 Chenshuang Zhang Kyeong Seon Kim Chengxin Liu Tae-Hyun Oh http://arxiv.org/abs/2606.01063v3 2026-08-24T06:41:51Z

Theory-of-Mind (ToM) reasoning enables embodied agents to understand human beliefs, goals, and intentions, but existing benchmarks mainly evaluate this ability through offline question answering or scenario-level action prediction. MindPower advances embodied ToM by introducing robot-centric reasoning from perception to action; however, it does not evaluate whether an agent can continuously interact with a changing environment and intervene only when assistance is needed. Building on MindPower, we introduce the MindHelper Challenge, which extends embodied ToM evaluation to real-time closed-loop precision intervention. An agent must continuously observe the environment, maintain actor-specific beliefs, identify when a human requires assistance, generate executable actions, and remain silent when intervention is unnecessary. We further propose MindClaw, a simple yet effective Claw-style framework that integrates an actor-specific Belief Table, embodied cognitive skills, and a Trigger-based cognitive dispatcher. Experiments show that MindClaw achieves 36.63% precise intervention rate and 14.36\% task accuracy, substantially outperforming direct VLM baselines, whose corresponding results remain below 12.05% and 3.80%.

2026-05-31T07:09:37Z Extended version of the CVPR 2026 paper *MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents*. This work is in progress Ruoxuan Zhang Qiaoqiao Wan Zhengguang Wang Chenghao Yu Hongxia Xie Wen-Huang Cheng Jianlong Fu http://arxiv.org/abs/2606.01014v1 2026-05-31T05:09:42Z

We address text-based 3D human motion editing, where the goal is to preserve the style and structure of a source motion while applying edits described in natural language. The release of the MotionFix dataset has spurred active research into training-based diffusion models that directly generate an edited motion from a source motion and a text instruction. While previous works have focused primarily on learning when an edit should occur temporally, our goal is to create a model that understands not only this temporal aspect but also which specific joints are responsible for the change. Targeting this, we propose a novel architecture and a complementary auxiliary task to aid its training. Our architecture consists of two axis-anchored transformers, which extract distinct features along the joint and time dimensions respectively, and a cross-axis fusion block that integrates these representations. We further introduce an auxiliary task that trains the joint-anchored transformer to regress the Soft-DTW distance between source and target joint rotations. This objective teaches the module to understand which joints to modify and which to preserve. Through comprehensive experiments on the MotionFix dataset, we demonstrate that our method significantly improves semantic alignment with both the text instruction and the source motion, as well as the overall fidelity of the generated motion, achieving state-of-the-art results.

2026-05-31T05:09:42Z CVPR 2026 Gyojin Han Junmo Kim http://arxiv.org/abs/2605.31591v1 2026-05-29T17:56:36Z

Models for AI-based skin cancer screening suffer a severe performance drop when shifting from expert dermoscopic (source) images to consumer-grade clinical (target) images, hindering real-world deployment. Existing domain adaptation methods often ignore crucial semantic invariants, such as clinical concepts. While new foundation models like MONET can provide this semantic information as dense, probabilistic scores, this metadata is unavailable at test time, creating a deployment paradox for practical image-only screening tools. We address this gap by proposing CoFiDA-M, a privileged information framework that learns from concepts at training time but deploys as an image-only model. Our method trains a teacher network that uses MONET concept probabilities to guide a FiLM modulator, transforming visual features into a semantically ``edited" feature space. A lightweight, image-only student is then trained to reproduce this edited representation, not just the teacher's final predictions. This distillation ``bakes" the clinical reasoning into the student's weights. On a challenging multi-dataset benchmark, our image-only student significantly outperforms state-of-the-art approaches, especially in melanoma recall. Our work provides a practical and generalizable framework for leveraging noisy, probabilistic metadata as privileged information, demonstrating strong cross-dataset robustness and potential for real-world deployment beyond dermatology. Implementation code is available at: https://github.com/mmu-dermatology-research/CoFiDA.git

2026-05-29T17:56:36Z 'Accepted by CVPR 2026' Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 15060-15069 Nurjahan Sultana Moi Hoon Yap Xinqi Fan Wenqi Lu http://arxiv.org/abs/2605.31227v1 2026-05-29T12:30:53Z

Procedural activities follow well-defined structures: whether we consider a cooking recipe or a mechanic repairing a car, these activities naturally decompose in a hierarchy of steps and sub-steps. Traditional approaches for step grounding require extensive annotations and scale poorly. Instead, we argue that such hierarchical structure can emerge naturally from uncurated videos of human activities through recurring patterns of co-occurring actions and activities. Our approach builds on HiERO, a weakly-supervised representation learning approach that maps close in the feature space actions that are functionally related to each other, leveraging only fine-grained action-level narrations. In this feature space, procedure steps can be detected by a simple clustering, with no additional task-specific fine-tuning. For the Ego4D Step Grounding challenge, we augment this approach by ensuring fine and coarse level agreement in step assignments, enforcing strict temporal monotonicity of the grounded steps and post-processing the detected steps to reduce the impact of noisy predictions. We call this approach HiERO-StepG and it achieves 56.27 % on the R@1 (IoU = 0.3) metric on the global leaderboard at submission time, ranking second while being completely zero-shot and not requiring procedure-specific annotations. Project page: https://github.com/andreazenotto/HiERO-StepG.

2026-05-29T12:30:53Z Technical report for the Ego4D Goal Step - Step Grounding challenge at CVPR 2026, derived from arXiv:2505.12911 Andrea Zenotto Simone Alberto Peirone Francesca Pistilli Giuseppe Averta http://arxiv.org/abs/2605.30339v1 2026-05-28T17:59:09Z

Generative video-to-audio (V2A) models produce highly plausible soundtracks, but it remains unclear whether they capture the underlying physical processes. Existing evaluations emphasize perceptual realism and overlook physical correctness under controlled interventions. In this paper, we introduce FlatSounds, a benchmark that audits the physical reasoning of V2A models through: 1) controlled counterfactual pairs in which a single physical factor is varied, and 2) single-video pattern tests that probe internal consistency and directional trends. These settings test whether the generated audio correctly reflects specific physical properties and timings. Our evaluation of state-of-the-art models reveals a consistent trade-off: models rely more on text captions than the visual stream to infer physics and semantics. Captions generally improve physical and semantic accuracy, but paradoxically degrade temporal alignment. Our results highlight the need to move beyond audio quality toward learning physical processes directly from pixels. Finally, we find that our physics-based metrics correlate strongly with human preference tests on our own data. Project webpage: https://research.nvidia.com/labs/cosmos-lab/flatsounds/

2026-05-28T17:59:09Z CVPR 2026 Tingle Li Siddharth Gururani Kevin J. Shih Gantavya Bhatt Sang-gil Lee Zhifeng Kong Arushi Goel Gopala Anumanchipalli Ming-Yu Liu http://arxiv.org/abs/2605.30311v1 2026-05-28T17:53:27Z

Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic modalities, including text, audio, motion, and visual content, remains an open challenge. In this paper, we present Archon, a fully pretrained, human-centric unified multimodal model for holistic avatar generation. Archon unifies seven modalities with modality-specific tokenizers, and a native autoregressive unified multimodal model pretrained on synchronized modalities and 72 diverse tasks to model holistic joint distributions. To address the token explosion challenge in high-fidelity talking videos, we introduce a memory-efficient semantic video reparameterization, achieving 4x token reduction while preserving fine-grained dynamics, coupled with a semantic-driven video diffusion decoder. We further propose a "Thinking in Modality" that decomposes ambiguous cross-modal tasks into stepwise thinking in an alternative chain of modality, progressively enhancing fidelity and controllability. Extensive experiments demonstrate that Archon achieves superior or comparable performance across diverse digital human generation tasks, validating the effectiveness of our unified framework. Project page: https://zju3dv.github.io/archon/.

2026-05-28T17:53:27Z Accepted to CVPR 2026. Project Page: https://zju3dv.github.io/archon/ Chong Bao Shichen Liu Lijun Yu David Futschik Stylianos Moschoglou Shefali Srivastava Ziqian Bai Feitong Tan Guofeng Zhang Zhaopeng Cui Sean Fanello Yinda Zhang http://arxiv.org/abs/2605.29602v1 2026-05-28T08:40:34Z

Multi-modal Retrieval-Augmented Generation (MMRAG) has emerged as a powerful paradigm for enhancing Multimodal Large Language Models in knowledge-intensive question answering by integrating external visual, textual, and structural knowledge. However, existing MMRAG frameworks suffer from critical limitations, including noisy and irrelevant retrieval, cross-modal semantic misalignment, lack of adaptive reasoning, and incoherent generation across local and global contexts. We introduce \textbf{CogniVerse}, a novel MMRAG framework that addresses these challenges through a cognitive-inspired, mathematically rigorous approach. Drawing from human-like reasoning, CogniVerse integrates three synergistic components: (1) a Cognitive Reflection Module that dynamically assesses retrieval necessity and filters relevant multi-modal content, reducing noise and computational overhead; (2) a Multi-modal Retrieval Module that aligns embeddings in a Riemannian manifold using information geometry and refines knowledge graphs via spectral graph theory, ensuring precise and coherent retrieval; and (3) a Hierarchical Generation Module that employs an optimal transport-based loss to balance token-level accuracy and global semantic coherence. Extensive experiments demonstrate that CogniVerse significantly outperforms state-of-the-art systems in both accuracy and coherence, while reducing retrieval latency.

2026-05-28T08:40:34Z Accepted in CVPR 2026 Xiang Fang Wanlong Fang Changshuo Wang http://arxiv.org/abs/2605.29318v1 2026-05-28T03:49:06Z

We present a novel formulation for mesh-free, reduced-order simulation of deformable hyperelastic objects. Existing work in reduced-order elastodynamic simulation represents the input geometry by either meshes, which can be difficult to obtain due to challenges in scanning and triangulating complex shapes, or by neural fields that require per-shape optimization. We propose to adopt a Reproducing Kernel Particle Method (RKPM) representation, which enables the construction of reduced-order skinning weights by solving a generalized eigensystem on the Hessian matrix of the elastic energy. We demonstrate that this formulation not only leads to a 40x training speedup compared with the per-shape optimization of neural fields, but also achieves lower simulation error when evaluated against the converged results of finite element method. We show our simulation results on a wide variety of objects in different representations including meshes and Gaussian splats, as well as the application of our method in the downstream task of robot simulation.

2026-05-28T03:49:06Z CVPR 2026, project website: https://research.nvidia.com/labs/sil/projects/freeform/ Donglai Xiang Vismay Modi Rishit Dagli Ty Trusty Gilles Daviet Anka He Chen Nicholas Sharp David I. W. Levin http://arxiv.org/abs/2605.28811v1 2026-05-27T17:59:02Z

We present a method for harmonizing the lighting of a foreground video to match a target background scene, adjusting shadows, color tone, and illumination intensity (relightful harmonization). Unlike images, acquiring labeled data for videos, where identical motions are recorded under different lighting conditions, is practically infeasible and non-scalable. While one way to create such paired data is to apply existing image-based harmonization models frame by frame to a video, the resulting outputs often suffer from significant temporal jitters. We overcome this problem by introducing a novel lighting deflickering model that can stabilize the global and local lighting flickering artifacts. Our video diffusion model learns from these upgraded deflickered data with a volume of real and synthetic videos to generate high-quality video harmonization results. We further propose an asymmetric alpha mask conditioning technique to learn the clean boundaries from real videos. Experiments demonstrate that our model achieves strong temporal coherence, naturalness, cleaner boundaries, and physically meaningful lighting behavior, while maintaining strong relighting expressiveness compared to prior image-based and video-based harmonization methods.

2026-05-27T17:59:02Z CVPR 2026 Jun Myeong Choi Jae Shin Yoon Luchao Qi Roni Sengupta Joon-Young Lee http://arxiv.org/abs/2605.28587v1 2026-05-27T15:09:55Z

Understanding dynamic 3D environments is essential for safe autonomous driving, particularly when reasoning about human-centric, nonrigid agents. However, existing weakly supervised occupancy prediction frameworks predominantly assume rigid-body motion and rely on simple frame-to-frame offsets, limiting their ability to capture fine-grained deformations and maintain temporal coherence. To address this issue, we propose DeGO, a deformable Gaussian occupancy framework that unifies decoupled Gaussian deformation with factorized 4D foundation-model distillation. DeGO disentangles rigid and nonrigid motion, enabling each Gaussian primitive to evolve through both deformation and offset-based updates. In parallel, a factorized 4D distillation strategy transfers cross-camera and cross-frame knowledge from the VGGT foundation model, producing foundation-aligned features that enhance temporal consistency. Experiments on the Occ3D-NuScenes benchmark demonstrate that our method achieves state-of-the-art performance under weak supervision, delivering 13.5% gains on human-centric instances and 10.9% overall improvements. These results highlight the effectiveness of deformation-aware and foundation-guided occupancy modeling for dynamic scene understanding. The code is publicly available: https://github.com/vita-epfl/DeGO

2026-05-27T15:09:55Z CVPR 2026 Yang Gao Wuyang Li Po-Chien Luan Alexandre Alahi http://arxiv.org/abs/2605.28067v1 2026-05-27T07:23:59Z

The remarkable generation quality of modern diffusion models often comes at the cost of massive parameter counts, which necessitate server-side inference with significant computational costs and potential privacy risks. Consequently, there is growing momentum toward developing efficient on-device alternatives. While recent efforts have optimized text-to-image models for mobile hardware, they remain relatively bulky, typically ranging from 0.5B to 1B parameters. We present BlazeEdit, a highly efficient, generalist image-to-image diffusion model tailored for on-device deployment. By identifying that many practical image editing tasks do not require text-based guidance, we eliminate the text-conditioning components and develop a multi-task architecture that consolidates object removal, outpainting, tone correction, relighting, and sticker generation into a single, compact model of only 195M parameters. BlazeEdit achieves a substantial reduction in download size and memory overhead while maintaining competitive generation quality. It completes a full inference pass in just 290ms on a Pixel 10, delivering a seamless, privacy-preserving, and lightning-fast experience for generalist image editing on the edge.

2026-05-27T07:23:59Z Accepted to CVPR 2026 EDGE Workshop Fei Deng Yanwu Xu Zhipeng Bao Zhixing Zhang Haolin Jia Karthik Raveendran Jianing Wei http://arxiv.org/abs/2605.27020v1 2026-05-26T13:38:25Z

The rapid advancement of diffusion-based image generation models has raised serious concerns regarding potential copyright and privacy infringements involving human-created data. Membership inference attacks (MIAs) have emerged as a promising tool for identifying unauthorized data usage during model training. Existing methods typically assess the ability of model to denoise perturbed suspect images as an indicator of membership status. However, the discriminative power of such features is highly dependent on the degree of model memorization and deteriorates significantly when applied to less exposed data (e.g., pre-training data). Although several methods attempt to enhance detection by leveraging internal model features, these features are generally inaccessible in mainstream closed-source image generation platforms, limiting their practicality. In this paper, we demonstrate that analyzing how a black-box diffusion model denoises a target image and corresponding perturbed textual instructions can reveal more distinctive membership cues. Based on this insight, we propose a black-box membership inference attack framework (named SD-MIA) that leverages a cross-modal data perturbation mechanism to detect pre-training data in diffusion models. We conduct extensive experiments on both a public benchmark dataset and a newly constructed dataset, each comprising pre-training membership and non-membership samples with identical distributions. Experimental results demonstrate that SD-MIA achieves superior performance compared to existing baselines, including those with the unfair advantage of accessing internal model features.

2026-05-26T13:38:25Z 13 pages, 9 figures; CVPR 2026 camera-ready Tao Qi Huili Wang Yuanhong Huang Wendan Wang Lianchao Zhao Jinrui Wang Zichen Qin Shangguang Wang Yongfeng Huang http://arxiv.org/abs/2605.26879v1 2026-05-26T11:38:36Z

Human motion recovered from monocular videos often appears overly smooth or dynamically inconsistent, even when joint positions are numerically accurate. We observe that this limitation stems from the absence of reliable high-order temporal cues -- velocity and acceleration -- which are essential for reconstructing motion that exhibits realistic momentum, timing, and high-frequency detail. We introduce HTD-Refine, a post-processing framework that augments existing Human Motion Recovery (HMR) pipelines using explicitly estimated high-order temporal dynamics. At the core of our system is PVA-Net, a temporal transformer that infers per-joint 2D positions, 3D velocities, and 3D accelerations directly from a monocular video. These predicted dynamics serve as soft yet informative constraints in a global optimization procedure that refines world-space trajectories, significantly reducing jitter, suppressing over-smoothing, and restoring physically plausible motion. Extensive experiments on challenging in-the-wild benchmarks show that HTD-Refine consistently improves state-of-the-art HMR methods, yielding more accurate global trajectories and substantially more natural motion dynamics. Our results highlight the critical role of high-order temporal modeling in advancing monocular human motion recovery.

2026-05-26T11:38:36Z 13 pages, 6 figures. Accepted as an Oral presentation and Best Paper Candidate at CVPR 2026. Project page: https://zju3dv.github.io/htd-refine/ Dingkun Wei Zehong Shen Yan Xia Georgios Pavlakos Yujun Shen Xiaowei Zhou http://arxiv.org/abs/2605.25304v1 2026-05-25T00:03:47Z

Concept Bottleneck Models (CBMs) have emerged as a cornerstone approach for interpretable machine learning, providing human-understandable intermediate representations through explicit concept activations. However, this interpretability fundamentally introduces a critical, previously unexplored attack surface: the concept bottleneck layer itself. We present a comprehensive, systematic study of concept-level adversarial vulnerabilities in CBMs, revealing that targeted, minimal perturbations operating on input pixels can induce catastrophic misclassification by manipulating semantic representations. We develop a rigorous theoretical framework to quantify concept-space robustness, establishing novel metrics that expose the vulnerability landscape of these architectures. Our extensive analysis on the CUB-200-2011 dataset demonstrates that standard CBMs exhibit severe susceptibility to concept-level manipulation. To address this critical weakness, we introduce SPECTRA (Semantic Perturbation-based Concept Training for Robustness against Attacks), a principled stability regularization defense. SPECTRA effectively hardens the semantic representation space, increasing the minimal perturbation norm required for a successful attack from 0.46 to over 4,200, rendering targeted concept manipulation computationally prohibitive. Furthermore, SPECTRA preserves baseline classification accuracy to within 2.2%. By establishing concept-level attacks as a fundamentally distinct threat model, this work opens a new research frontier at the intersection of interpretable machine learning and adversarial robustness.

2026-05-25T00:03:47Z Accepted to CVPR 2026 (Findings). 9 pages, 6 figures Aditya Sridhar http://arxiv.org/abs/2605.25220v1 2026-05-24T19:09:15Z

High-fidelity 3D Gaussian head avatar generation is critical for applications such as AR/VR, telepresence, and digital humans. Existing methods depend on multi-view datasets, 3D captures, or intermediate 2D view synthesis. In contrast, we learn both conditional and unconditional 3D head models from randomly sampled 2D images alone, without using multi-view data, 3D supervision, or intermediate view generation. We introduce MVCHead, a single-shot state space model that enforces multi-view consistency (MVC) directly in the 3D representation while regressing 3D Gaussians under these constraints. At its core, we propose a Hierarchical State Space (HiSS) block that progressively refines Gaussians from coarse to fine, while capturing long-range dependencies. Within each HiSS block, we modify Mamba's standard unidirectional scan with the proposed Hierarchical Bi-directional State Scan (HiBiSS) that aligns recurrence with the axes along which multi-view inconsistencies are strongest. Finally, we design an SE(3) Multi-view Critic that judges whether a set of self-renders arises from a single underlying 3D configuration, rewarding cross-view pixel alignment without observing real multi-view pairs. MVCHead achieves state-of-the-art perceptual quality, surpasses prior methods in both texture and geometric consistency, and maintains comparable shape consistency. To demonstrate scalability, we release FaceGS-10K, the first large-scale dataset of ready-to-use 3D Gaussian head assets for training and evaluation of 3D head models. Project Page and code: https://humansensinglab.github.io/MVCHead/

2026-05-24T19:09:15Z CVPR 2026; Project Website: https://humansensinglab.github.io/MVCHead/ CVPR, Denver, CO, USA, 2026, pp. 40163-40174 Aviral Chharia Fernando De la Torre http://arxiv.org/abs/2605.27451v1 2026-05-24T17:44:37Z

The 10th Affective & Behavior Analysis in-the-Wild (ABAW) Workshop and Competition, held at CVPR 2026, continues to advance research on modelling, analysis, understanding of human affect and behavior in real-world, unconstrained environments. The workshop maintains its dual structure, comprising both a competition and a paper track. The ABAW Competition introduces a diverse set of challenges targeting key aspects of affective and behavioral understanding, including continuous affect (valence-arousal) estimation, discrete affect (expression and action unit) recognition, as well as more complex behavior analysis tasks, such as emotional mimicry intensity estimation, ambivalence/hesitancy recognition and fine-grained violence detection. These challenges are built upon large-scale in-the-wild datasets, providing comprehensive benchmarks for state-of-the-art approaches. In parallel, the paper track presents a wide range of contributions spanning pose, motion & behavior estimation, affect modelling & multimodal learning, benchmarks, datasets & evaluation protocols, fairness, robustness & deployment. Overall, the 10th ABAW Workshop and Competition continues to serve as a key platform for benchmarking, collaboration and innovation, shaping the development of next-generation multimodal, human-centered AI systems.

2026-05-24T17:44:37Z accepted at CVPR 2026 Dimitrios Kollias Panagiotis Tzirakis Alan Cowen Stefanos Zafeiriou Irene Kotsia Eric Granger Marco Pedersoli Simon Bacon Jens Madsen Soufiane Belharbi Muhammad Haseeb Aslam Chunchang Shao Guanyu Hu http://arxiv.org/abs/2605.24762v1 2026-05-23T22:49:04Z

High-resolution datasets are essential for advancing super-resolution (SR) and text-to-image (T2I) diffusion research. However, current publicly available datasets lack both the native 4K resolution and the extensive scale necessary for training state-of-the-art models. To address this gap, we introduce a 4K Large Scale Dataset and Benchmark (4KLSDB), a large-scale, diverse dataset consisting of 129,484 carefully curated 4K resolution images spanning multiple categories such as nature, urban scenes, people, food, artwork, and CGI, alongside distinct validation and test sets containing 2,000 and 1,984 images respectively. Images were sourced from established open datasets including Photo Concept Bucket, Laion2B, and PD12M. 4KLSDB underwent rigorous multi-stage automated filtering and annotation pipelines involving both human annotators and Large Multimodal Models (LMMs) to ensure high aesthetic quality and dataset consistency. We demonstrate 4KLSDB's effectiveness by training representative super-resolution and diffusion models, observing significant improvements in performance on native 4K benchmarks. Comprehensive experiments illustrate a positive correlation between training on true 4K resolution data and improved fidelity in image restoration task, especially on 4K resolution. We provide the research community a valuable resource to drive progress toward genuinely high-fidelity image synthesis and restoration by providing 4KLSDB. Our project page is available at: https://4klsdb.github.io/.

2026-05-23T22:49:04Z Accepted to the DataCV Workshop at CVPR 2026; 10 pages, 4 figures, 7 tables; Our project page is available at: https://4klsdb.github.io/ Zihao Zhu Kuan-Ru Huang Zhaoming Xu Renjie Li Bo Wu Ruizheng Bai Mingyang Wu Sayak Paul Zhengzhong Tu http://arxiv.org/abs/2605.24456v2 2026-05-26T08:53:56Z

Humans constantly reason about 3D proximity, the relations between their body and surrounding objects, to guide perception and action in daily life. Whether multimodal large language models (MLLMs) can perform such embodied 3D reasoning remains unclear. To this end, we introduce EgoProx, a benchmark for egocentric 3D proximity reasoning. We organize our tasks along a cognitive chain, covering intention, exploration, exploitation, and chain-of-actions reasoning. We also design an agent based data engine that produces diverse and consistent QA pairs at scale. We benchmark prevailing MLLMs on EgoProx and conduct additional analyses with dataset specific and task specific instruction tuning. We observe large cross-domain gains, indicating that current MLLMs contain some spatial knowledge; however, they still struggle to effectively leverage it for spatial reasoning VQA.

2026-05-23T08:07:45Z Accepted to CVPR 2026 Jinzhao Li Yinuo Chen Dongxu Piao Panwang Pan Yifan Yu Dong Wang Honglei Yan Liang Yue Shaofei Wang Yixin Chen Siyuan Huang Miao Liu http://arxiv.org/abs/2605.23216v2 2026-07-02T06:54:56Z

Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception to a deeper understanding of causal mechanisms. However, existing benchmarks rarely provide the fine-grained, grounded evidence needed to rigorously evaluate this capability. To address this gap, we introduce CaST-Bench, a benchmark for Causal Chain-Grounded Spatio-Temporal Video Reasoning. CaST-Bench presents complex causal questions that require models to identify and localize a chain of multiple spatio-temporal evidences. Through a human-AI collaborative pipeline, we construct a high-quality dataset of 2,066 questions over 1,015 videos, with causal chains annotated by temporal segments and bounding-box tracks. Furthermore, we design a comprehensive evaluation suite with novel metrics that assess not only answer correctness but also the capability for visual evidence grounded reasoning. This grounding is crucial for improving accuracy by mitigating spurious correlations and for enhancing user trust by making models more transparent. Our experiments show that current VLMs struggle with causal questions, largely due to their limited ability to construct precise and grounded causal chains. This highlights an important direction for improving future VLMs. Homepage: https://woven-by-toyota.github.io/CaST-Bench.

2026-05-22T04:19:29Z CVPR 2026 Mingfang Zhang Jingjing Pan Ashutosh Kumar Rajat Saini Mustafa Erdogan Hsuan-Kung Yang Caixin Kang Yifei Huang Yoichi Sato Quan Kong http://arxiv.org/abs/2605.23141v1 2026-05-22T01:43:32Z

A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipulate concept-level properties under transformation and transfer them to new scenes. We introduce VisAnalog, a controlled suite for this setting on natural images. Each example instantiates $A\!:\!B::C\!:\,?$: images $B$ and a hidden target image $D$ are produced by applying the same deterministic transformation sequence to source images $A$ and $C$. Given $A$, $B$, and $C$, a model must answer a multiple-choice question about $D$. The benchmark contains 617 human-validated questions spanning one- to four-step transformations such as zoom, quadrant swap, rotation, flip, and hue rotation. Across strong proprietary and open-source VLMs, end-to-end accuracy is substantially lower than oracle accuracy when $D$ is directly shown, and degrades sharply as transformation depth increases, while human performance remains near the ceiling. A program-conditioned evaluation further separates failures of relation inference from failures of transformation application, showing that inferring the visual relation from $A \rightarrow B$ is the dominant bottleneck, with additional application errors emerging on harder multi-step cases. The dataset is publicly available at https://huggingface.co/datasets/zli99/VisAnalog.

2026-05-22T01:43:32Z Accepted to the Workshop on Visual Concepts at CVPR 2026 as a non-archival report Zhaonan Li Kyle R. Chickering Bangzheng Li Jacob Dineen Xiao Ye Zhikun Xu Shijie Lu Yuxi Huang Ming Shen Bach Nguyen Jaya Adithya Pavuluri Mau Son Nguyen Sanika Chavan Ngoc Minh Thu Le Muhao Chen Ben Zhou http://arxiv.org/abs/2605.22997v1 2026-05-21T19:52:22Z

In autonomous driving, mapping is critical for motion planning but remains an under-utilized resource for perception tasks such as 3D object detection. Maps can provide robust structural priors of the static environment, helping resolve ambiguities and correct for sensor data sparsity or noise, especially for distant objects or under adverse weather conditions. However, conventional High-Definition (HD) maps are resource-intensive to obtain and maintain, which presents a challenge for efficient, large-scale deployment. In this paper, we propose a scalable solution to systematically leverage mapping to improve 3D detection by overcoming two primary challenges. First, we introduce a pipeline to automatically build dense mapping priors from aggregated sensor data, eliminating the need for human labeling. Second, we design a novel Mapping Priors Augmented 3D Detection (MPA3D) framework to effectively integrate mapping priors with different sensor modalities. Extensive experiments on the Waymo Open Dataset demonstrate that our approach achieves new state-of-the-art results, proving the effectiveness of scalable reconstructed scene priors for enhancing 3D detection.

2026-05-21T19:52:22Z Accepted to CVPR 2026 Yang Fu Yuliang Zou Hao Xiang Xin Huang Yijing Bai Chen Song Weijing Shi Govind Thattai Dragomir Anguelov Mingxing Tan Yingwei Li http://arxiv.org/abs/2605.21625v1 2026-05-20T18:36:57Z

The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus predominantly on coarse-grained tasks such as action segmentation, classification, captioning, and retrieval. Furthermore, these benchmarks often rely on entities that can be easily identified verbally, like household objects, animals, human subjects, etc., limiting their applicability to complex, in-the-wild video scenarios. But, many applications such as furniture assembly, cooking, etc., require step-by-step fine-grained spatio-temporal understanding of the video, which is not sufficiently evaluated in current benchmarks. To address this gap, we introduce Flat-Pack Bench, a novel benchmark centered on furniture assembly tasks. Our benchmark evaluates LVLMs on nuanced tasks, including temporal ordering of assembly actions, temporal localization of assembly state, understanding part mating, and tracking, using multiple-choice questions paired with visual prompts highlighting relevant parts as references for fine-grained questions. Our experiments reveal that state-of-the-art LVLMs struggle significantly with fine-grained spatio-temporal reasoning, highlighting their limitations in effectively leveraging temporal information from videos, limited tracking ability, and understanding of spatial interactions like physical contact.

2026-05-20T18:36:57Z CVPR 2026 Aditya Chetan Eric Cai Peeyush Kushwaha Bharath Raj Nagoor Kani Utkarsh Mall Qianqian Wang Noah Snavely Bharath Hariharan http://arxiv.org/abs/2605.19620v1 2026-05-19T09:56:52Z

LiDAR-based 3D human motion capture has broad applications in fields such as autonomous driving and robotics, where accurate motion reconstruction is crucial. However, existing methods often struggle with unstable inputs and severe occlusions, leading to jittery or even failed pose predictions. To address these challenges, we propose BMLiCap, a coarse-to-fine framework that models motion using temporally compressible Bézier curves. By reducing control points through a trajectory-preserving strategy, we obtain a coherent and learning-friendly motion representation. To reconstruct human actions from LiDAR point-cloud cues, we design a progressive motion-reconstruction module. Specifically, a Time-scale Motion Transformer (TMT) is introduced to predict motion curves at multiple temporal scales, and a Multi-level Motion Aggregator (MMA) is utilized to adaptively fuse the multi-scale curves to recover detailed, temporally coherent poses, effectively bridging observation gaps caused by occlusions and noise. Across four mainstream benchmarks LiDARHuman26M, FreeMotion, NoiseMotion, and SLOPER4D, BMLiCap achieves state-of-the-art accuracy and temporal continuity in complex scenes, demonstrating its ability to compensate for severe occlusions and reduce prediction jitter.

2026-05-19T09:56:52Z Accepted by CVPR 2026 Xiaoqi An Lin Zhao Jun Li Chen Gong Jian Yang http://arxiv.org/abs/2605.18680v1 2026-05-18T17:21:43Z

Metaverse platforms rely on creator-driven marketplaces where avatars are assembled from discrete, taxonomy-labeled 3D assets (e.g., tops, bottoms, shoes, accessories) under strict category and topology constraints. While users increasingly expect free-form text control, text-only retrieval is brittle: natural language is ambiguous with respect to platform taxonomies, metadata is often noisy or informal, and independently retrieved components can be stylistically inconsistent or geometrically incompatible. We propose \textbf{CMAG}, a concept-scaffolded retrieval and verified composition framework for marketplace avatar generation. Given a prompt, CMAG first synthesizes an intermediate 3D concept scaffold that disambiguates intent beyond text by providing global spatial and stylistic context. In parallel, a view-aware part discovery module extracts localized visual evidence via prompt decomposition and text-grounded segmentation. A prompt-conditioned taxonomy router enforces category coverage and resolves semantic-to-taxonomic mismatch, after which a hybrid category-wise retriever combines part-based fusion with a concept-residual fallback using feature suppression. Finally, an agentic vision--language model filters and re-ranks candidates across categories and drives an iterative verification loop to assemble prompt-faithful, topologically consistent avatars from catalog assets. We evaluate CMAG on diverse compositional prompts and demonstrate improved retrieval robustness and compositional correctness compared to strong baselines, highlighting the importance of 3D concept scaffolding under prompt ambiguity.

2026-05-18T17:21:43Z Accepted to CVPR 2026 Workshop (GRAIL-V) Rajeev Goel Jason Ding Phani Harish Wajjala Pavan Turaga Tejaswi Gowda Krishna C. Garikipati http://arxiv.org/abs/2605.17014v1 2026-05-16T14:25:42Z

Reconstructing people, objects, and their interactions in 3D is a long-standing goal for intelligent systems. Often the input is RGB video from a moving camera, making the task ill-posed; depth is ambiguous, humans and objects occlude each other, and camera and object motion entangle to create apparent motion. Most prior work addresses humans or objects in isolation, ignoring their interplay, or assumes known 3D shapes or cameras, which is impractical for real-world applications. We develop RHINO (Reconstructing Human Interactions with Novel Objects), a three-step framework that recovers in 3D a human, novel (unseen) manipulated object, and static scene in a common world frame from a monocular RGB video. First, we leverage 3D-aware foundation models to obtain cues that stabilize Structure-from-Motion (SfM) even for low-texture regions; this yields a coarse shape and apparent motion of a manipulated object from foreground pixels, and a coarse scene shape and camera motion from background pixels. Second, we estimate a human in the camera frame via an off-the-shelf method, and subtract the camera motion from apparent motion to extract the object motion; this registers the human, object, and coarse scene shapes into a common world frame. Third, we refine shapes using a compositional neural field with per-component signed-distance fields. The latter further enables differentiable contact priors that attract surfaces while penalizing interpenetration, improving the physical plausibility of the final reconstruction. For evaluation, we capture a new dataset of handheld monocular videos synchronized with a volumetric 4D capture stage, providing ground-truth shape and camera motion. RHINO outperforms state-of-the-art baselines on novel-view synthesis and 4D reconstruction. Ablations show that each stage contributes substantially. Code and data are available at https://lxxue.github.io/RHINO.

2026-05-16T14:25:42Z CVPR 2026. Project page: https://lxxue.github.io/RHINO Lixin Xue Chengwei Zheng Georgios Paschalidis Chen Guo Manuel Kaufmann Juan Zarate Dimitrios Tzionas http://arxiv.org/abs/2605.14569v1 2026-05-14T08:39:42Z

Reconstructing dynamic visual experiences as videos from functional magnetic resonance imaging (fMRI) is pivotal for advancing the understanding of neural processes. However, current fMRI-to-video reconstruction methods are hindered by a semantic gap between noisy fMRI signals and the rich content of videos, stemming from a reliance on incomplete semantic embeddings that neither capture video-specific cues (e.g., actions) nor integrate prior knowledge. To this end, we draw inspiration from the dual-pathway processing mechanism in human brain and introduce CineNeuron, a novel hierarchical framework for semantically enhanced video reconstruction from fMRI signals with two synergistic stages. First, a bottom-up semantic enrichment stage maps fMRI signals to a rich embedding space that comprehensively captures textual semantics, image contents, action concepts, and object categories. Second, a top-down memory integration stage utilizes the proposed Mixture-of-Memories method to dynamically select relevant "memories" from previously seen data and fuse them with the fMRI embedding to refine the video reconstruction. Extensive experimental results on two fMRI-to-video benchmarks demonstrate that CineNeuron surpasses state-of-the-art methods across various metrics.

2026-05-14T08:39:42Z Accepted to CVPR 2026 Yujie Wei Chenglong Ma Jianxiong Gao Chenhui Wang Shiwei Zhang Biao Gong Shuai Tan Hangjie Yuan Hongming Shan http://arxiv.org/abs/2605.10858v1 2026-05-11T17:05:49Z

Today's driving world models can generate remarkably realistic dash-cam videos, yet no single model excels universally. Some generate photorealistic textures but violate basic physics; others maintain geometric consistency but fail when subjected to closed-loop planning. This disconnect exposes a critical gap: the field evaluates how real generated worlds appear, but rarely whether they behave realistically. We introduce WorldLens, a unified benchmark that measures world-model fidelity across the full spectrum, from pixel quality and 4D geometry to closed-loop driving and human perceptual alignment, through five complementary aspects and 24 standardized dimensions. Our evaluation of six representative models reveals that no existing approach dominates across all axes: texture-rich models violate geometry, geometry-aware models lack behavioral fidelity, and even the strongest performers achieve only 2-3 out of 10 on human realism ratings. To bridge algorithmic metrics with human perception, we further contribute WorldLens-26K, a 26,808-entry human-annotated preference dataset pairing numerical scores with textual rationales, and WorldLens-Agent, a vision-language evaluator distilled from these judgments that enables scalable, explainable auto-assessment. Together, the benchmark, dataset, and agent form a unified ecosystem for assessing generated worlds not merely by visual appeal, but by physical and behavioral fidelity.

2026-05-11T17:05:49Z CVPR 2026 VideoWorldModel Workshop; Project Page at https://worldbench.github.io/worldlens GitHub at https://github.com/worldbench/WorldLens Lingdong Kong Ao Liang Tianyi Yan Hongsi Liu Wesley Yang Ziqi Huang Xian Sun Wei Yin Jialong Zuo Yixuan Hu Dekai Zhu Dongyue Lu Youquan Liu Guangfeng Jiang Linfeng Li Xiangtai Li Long Zhuo Lai Xing Ng Benoit R. Cottereau Changxin Gao Liang Pan Wei Tsang Ooi Ziwei Liu http://arxiv.org/abs/2605.16385v3 2026-06-16T22:53:58Z

Geometric problem solving, as a typical multimodal reasoning problem, has attracted much attention and made great progress recently, however most of works focus on plane geometry while usually fail in solid geometry due to 3D spatial diagrams and complex reasoning. To bridge this gap, we introduce Hilbert-Geo, the first unified formal language framework for solid geometry, including an extensive predicate library and a dedicated theorem bank. Based on this framework, we propose a Parse2Reason method containing two steps of first parsing then reasoning. In the parsing step, we utilize conditional description language (CDL), a formalized language composed of predicates specifically designed to construct geometric conditions, to represent both problem description (natural text) and solid diagrams (visual image). In the reasoning step, we leverage those formal CDL and the theorem bank to perform relational inference and algebraic computation, generating strictly correct, verifiable, and human-readable reasoning processes. Notably, our proposed Hilbert-Geo is also applicable to plane geometry. To advance geometric reasoning, we curate two expert-annotated dataset SolidFGeo2k and PlaneFGeo3k, which are furnished with geometric formal language annotations, solutions and answers. Extensive experiments show that our proposed method achieves the state-of-the-art (SOTA) performance 77.3% in SolidFGeo2k and 84.1% in MathVerse-Solid (one small subset in MathVerse dedicated to solid geometry), substantially outperforming leading MLLMs, such as Gemini-2.5-pro (54.2% on SolidFGeo2k) and GPT-5 (62.9% on MathVerse-Solid). In addition, our method achieves the SOTA accuracy 80.2% in PlaneFGeo3k, demonstrating the generality of the Hilbert-Geo in geometric reasoning. Our code and datasets are released at https://github.com/PremiLab-Math/Hilbert-Geo.

2026-05-11T13:42:41Z Computer Vision and Pattern Recognition (CVPR), 2026 Ruoran Xu Haoyu Cheng Bin Dong Qiufeng Wang http://arxiv.org/abs/2605.10523v1 2026-05-11T13:10:07Z

The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, especially when generating long videos or modeling intensive motions. Existing human image animation works address these issues by incorporating human-specific semantic representations, e.g., dense poses or ID embeddings, as additional conditions. However, conditioning on these representations could decrease the generation flexibility. Moreover, their reliance on RGB pixel supervision also lacks emphasis on learning necessary 3D geometric relationships and temporal coherence. In contrast, we introduce a novel approach named SemanticREPA that leverages these semantic representations as supervision signals through representation alignment. Specifically, we begin by training a structure alignment module that aligns the structure representations obtained from video latents with video depth estimation features. We then fix the pretrained module, and utilize it to provide additional supervision on the structure representations of the diffusion models, achieving structure rectification to generate coherent and stable human structures. Simultaneously, we develop an ID alignment module to align the ID representations of the generated videos to face recognition features. We further propose to use the predicted structure representations to refine identity restoration in relevant regions. With structure and ID alignment, our method demonstrates superior quality on extended character motions and enhanced character consistency.

2026-05-11T13:10:07Z Accepted by CVPR 2026 workshop Chang Liu Mengting Chen Yixuan Huang Haoning Wu Chen Ju Shuai Xiao Jinsong Lan Yanfeng Wang http://arxiv.org/abs/2605.10204v1 2026-05-11T08:51:28Z

Accurate 3D reconstruction of objects with reflective, transparent, or low-texture surfaces still remains notoriously challenging. Such materials often violate key assumptions in multi-view reconstruction pipelines, such as photometric consistency and the availability on distinct geometric texture cues. Existing datasets primarily focus on diffuse, textured objects, and therefore provide limited insight into performance under real-world material complexities. We introduce 3DReflecNet, a large-scale hybrid dataset exceeding 22 TB that is specifically designed to benchmark and advance 3D vision methods for these challenging materials. 3DReflecNet combines two types of data: over 120,000 synthetic instances generated via physically-based rendering of more than 12,000 shapes, and over 1,000 real-world objects captured using consumer devices. Together, these data consist of more than 7 million multi-view frames. The dataset spans diverse materials, complex lighting conditions, and a wide range of geometric forms, including shapes generated from both real and LLM-synthesized 2D images using diffusion-based pipelines. To support robust evaluation, we design benchmarks for five core tasks: image matching, structure-from-motion, novel view synthesis, reflection removal, and relighting. Extensive experiments demonstrate that state-of-the-art methods struggle to maintain accuracy across these settings, highlighting the need for more resilient 3D vision models.

2026-05-11T08:51:28Z This paper has been accepted by CVPR 2026 Oral Zhicheng Liang Haoyi Yu Boyan Li Dayou Zhang Zijian Cao Tianyi Gong Junhua Liu Shuguang Cui Fangxin Wang http://arxiv.org/abs/2605.10127v2 2026-05-13T05:54:11Z

Recent research work on fashion outfit generation focuses on promoting visual consistency of garments by leveraging key information from reference image and text prompt. However, the potential of outfit generation remains underexplored, requiring comprehensive e-commercial dataset and elaborative utilization of multi-modal condition. In this paper, we propose a brand-new e-commerce dataset, named Fashion130k, with various occasions, models, and garment types. For the consistent generation of garment, we design a framework with Unified Multi-modal Condition (UMC) to align and integrate the text and visual prompts into generation model. Specifically, we explore an embedding refiner to extract the unified embeddings of multi-modal prompts, within which a Fusion Transformer is proposed to align the multi-modal embeddings by adjusting the modality gap between text and image. Based on unified embeddings, the attention in generation model is redesigned to emphasis the correlations between prompts and noise image, inducing that the noise image can select the pivotal tokens of prompts for consistent outfit generation. Our dataset and proposed framework offer a general and nuanced exploration of multi-modal prompts for generation models. Extensive experiments on real-world applications and benchmark demonstrate the effectiveness of UMC in visual consistency, achieving promising result than that of SoTA methods.

2026-05-11T07:40:03Z Accepted to CVPR 2026 Findings Yu He Ting Zhu Yichun Liu Lichen Ma Xinyuan Shan Jingling Fu Yu Shi Junshi Huang Yan Li http://arxiv.org/abs/2605.09703v1 2026-05-10T18:51:34Z

Understanding human mental states from natural behavior is crucial for intelligent systems in the real world. However, most current research focuses on predicting isolated mental state labels, lacking structured annotations of complex interpersonal interactions. To support structured analysis, we introduce MOTOR-Bench, a carefully-designed benchmark with a real-world dataset MOTOR-dataset, containing 1,440 multimodal video clips in collaborative learning scenarios, reflecting key real-world data challenges including natural class imbalance, visual noise, and domain-specific language. Each sample is labeled by educational experts based on self-regulated learning theory. We further evaluate several state-of-the-art multimodal large language models and multi-agent systems in a zero-shot setting on our MOTOR-Bench. However, their performance on this task remains limited, suggesting that existing methods still struggle with structured reasoning from observable behavior to deeper mental states. To address this challenge, we propose a reasoning multi-agent framework, named MOTOR-MAS. It coordinates multiple agents through a structured agent coordination mechanism to infer explicit behaviors, internal cognitions, and psychological emotions. Experimental results show that our MOTOR-MAS outperforms the best single-model benchmark by 15.93 points in Macro-F1 scores for the three labels of behavior, cognition, and emotion, and outperforms the general multi-agent benchmark by 10.2 points in internal cognition prediction.

2026-05-10T18:51:34Z Accepted by CVPR 2026 workshop AI4RWC Xiaoyu Yuan Niklas Heikkala Tiina Törmänen Hanna Järvenoja Guoying Zhao Haoyu Chen http://arxiv.org/abs/2605.09233v2 2026-06-01T19:32:07Z

Recent advances in visual generative models have enabled high-fidelity image editing guided by human instructions. However, these models often struggle with complex instructions involving combinatorial editing operations or inter-step dependencies. This difficulty stems from the limitations of two canonical paradigms: (1) single-turn editing, which attempts to apply all instructed edits in one pass, often fails to parse the complex instruction accurately and causes undesired edits; and (2) sequential editing can decompose the task into simpler steps but suffers from compounding errors introduced by the sequential execution, leading to low-fidelity results. To derive a robust solution for complex image editing, we examine editing behaviors of different paradigms under a unified in-context editing framework, and study how the benefits of sequential decomposition can be balanced against its error-accumulation drawbacks. We further develop a synthetic data pipeline that constructs editing tasks of varying instruction complexity, allowing us to curate a large-scale editing dataset with high-quality decomposed sequences. By finetuning on synthetic data, we discovered that with properly designed editing paradigms, sequential decomposition yields robust improvements even as task complexity increases. Furthermore, the decomposition skills learned from synthetic tasks can transfer to real images by co-training with real-world editing data, demonstrating the promise of sim-to-real generalization for tackling complex image editing across broader domains.

2026-05-10T00:23:05Z CVPR 2026 Zilai Zeng Mingdeng Cao Zijie Li Xiaochen Lian Yichun Shi Peihao Zhu Chen Sun Peng Wang http://arxiv.org/abs/2605.08841v1 2026-05-09T09:52:23Z

Vision-Language Models (VLMs) exhibit systematic bias toward visual illusions, recalling memorized facts rather than perceiving actual visual differences. This paper presents a training-free framework for the 5th DataCV Challenge Task 1 at CVPR 2026, addressing this perception-versus-memory conflict through three complementary strategies:(1) illusion-aware image preprocessing that weakens illusion-inducing context via type-specific transformations (edge extraction, color isolation, morphological processing, and reference-line overlay), (2) anti-illusion prompt engineering guiding VLMs toward qualitative visual comparison, and (3) multi-vote ensemble that further improves robustness. Our method achieves 90.48% accuracy on the official 630-image test set using Claude (claude-opus-4-6) with 5-vote majority ensemble, and 98.41% on a human-verified subset. The approach requires no finetuning, relying solely on visual manipulation and prompt design. Our solution secured 2nd place in the challenge, only 0.47% behind the 1st-place solution. Code is available at https://github.com/jasminezz/sf-illusion-aware-vlm.git.

2026-05-09T09:52:23Z Accepted at CVPR 2026 Workshop on 5th DataCV Challenge Junli Zha Jiahui Wang Xinkai Lu Jinbo Wang http://arxiv.org/abs/2607.14115v1 2026-05-08T12:04:43Z

Inspired by how humans communicate spatial information, language-guided geo-localization has gained significant traction for its intuitive and practical value. Despite this progress, most methods still rely on a static, one-shot retrieval paradigm, which fails to handle the ambiguity and incompleteness inherent in real-world natural language descriptions. We propose a paradigm shift to reasoning retrieval and introduce Dialogue Place Recognition (DlgPR), which casts localization as an interactive, dialogue-driven reasoning process. To support this new task, we present DlgQuest-Cities, the first large-scale dialogue-based benchmark for place recognition, and a unified reasoning framework that couples a cross-modal multi-level retriever with an intelligent questioner, DQ-pilot. DQ-pilot is trained in a curriculum: supervised fine-tuning on a curated DQ-cities-20k subset followed by reinforcement refinement on a harder DQ-cities-10k split via GRPO. Two task-aligned metrics guide learning: a Discriminative Difficulty Index (DDI) for curriculum sampling and a Positional Retrieval Gain (PRG) reward that directly measures retrieval improvement induced by a question. Experiments show this reasoning-based approach significantly outperforms baselines. The code and model are available at https://github.com/Graysonggg/DlgPR.

2026-05-08T12:04:43Z Accepted to CVPR 2026 Yukun Song Changwei Wang Xingtian Pei Shibiao Xu Wenhao Xu Shunpeng Chen Yu Zhang Ke Zhang Rongtao Xu Xuxiang Feng Pengyang Wang http://arxiv.org/abs/2605.07552v2 2026-05-12T08:12:04Z

The rapid advances in deep learning have significantly enhanced the accuracy of multimodal 3D human pose estimation (HPE). However, the state-of-the-art (SOTA) HPE pipelines still rely on Transformers, whose quadratic complexity makes real-time processing for long sequences impractical. Mamba addresses this issue through selective state-space modeling, enabling efficient sequence processing without sacrificing representational power. Nevertheless, it struggles to capture complex spatial dependencies in multimodal settings. To bridge this gap, we propose VIMCAN, a hybrid architecture that combines the efficient sequence modeling of Mamba with the spatial reasoning of Cross-Attention, and performs robust visual-inertial fusion and human pose estimation between RGB keypoints and wearable IMU data. By leveraging Mamba's dynamic parameterization for temporal modeling and Attention for spatial dependency extraction, VIMCAN achieves superior accuracy, with mean per-joint position errors (MPJPE) of 17.2 mm on TotalCapture and 45.3 mm on 3DPW. VIMCAN outperforms prior Transformer-based and other SOTA approaches while supporting real-time inference at over 60 frames per second on consumer-grade hardware. The source code is available at \href{https://github.com/Eddieyzp/VIMCAN}{this GitHub repository}.

2026-05-08T10:28:05Z Accepted in CVPR 2026 Zepeng Yang Junxuan Bai Hao Li Ju Dai Junjun Pan Yongfeng Yin Bin Li http://arxiv.org/abs/2605.07256v1 2026-05-08T05:24:51Z

Transformer architecture search (TAS) discovers optimal vision transformer (ViT) architectures automatically, reducing human effort to manually design ViTs. However, existing TAS methods suffer from the feature collapse problem, where subnets within a supernet fail to learn subnet-specific features, mainly due to the shared weights in a supernet, limiting the performance of individual subnets. To address this, we propose TAS-LoRA, a novel method that introduces parameter-efficient low-rank adaptation (LoRA) to enable subnet-specific feature learning, while maintaining computational efficiency. TAS-LoRA incorporates a Mixture-of-LoRAExperts (MoLE) strategy, where a lightweight router dynamically assigns LoRA experts based on subnet architectures, and introduces a group-wise router initialization technique to encourage diverse feature learning across experts early in training. Extensive experiments on ImageNet and several transfer learning benchmarks, including CIFAR-10/100, Flowers, CARS, and INAT-19, demonstrate that TAS-LoRA mitigates feature collapse effectively, improving performance over state-of-the-art TAS methods significantly.

2026-05-08T05:24:51Z Accepted to CVPR 2026 Jeimin Jeon Hyunju Lee Bumsub Ham http://arxiv.org/abs/2605.06049v1 2026-05-07T11:34:41Z

As a key technique in multi-modal processing, infrared and visible image fusion (IVIF) plays a crucial role in integrating complementary spectral information for visual enhancement and downstream vision tasks. Despite remarkable progress, existing methods struggle to flexibly accommodate heterogeneous demands. Achieving adaptive fusion that aligns with various preferences from both human and machine vision remains an open and challenging problem. To address this challenge, we propose DPOFusion, a direct preference optimization (DPO) framework integrating the property-aligned latent diffusion model (PALDM) and the preference-controllable latent diffusion model (PCLDM), enabling task-guided, preference-adaptive IVIF for both human and machine vision. The PALDM leverages a latent fusion prior and a joint conditional loss to generate diverse candidate fusion results with various properties. PCLDM is subsequently fine-tuned via instance direct preference optimization (IDPO), enabling direct control of the final fusion results with heterogeneous preference signals. Experimental results demonstrate that our framework not only attains precise preference alignment among humans, vision-language models, and task-driven networks, but also sets a new benchmark for adaptive fusion quality and task-oriented transferability.

2026-05-07T11:34:41Z Accepted by CVPR 2026 Weijian Su Songqian Zhang Yuqi Han Jian Zhuang Yongdong Huang Qiang Zhang http://arxiv.org/abs/2605.05390v1 2026-05-06T19:23:22Z

Tracking 3D human motion from egocentric multi-camera headset is challenged by severe egomotion, partial visibility or occlusions and lack of training data. Existing methods designed for monocular video often require static or slowly-moving cameras and cannot efficiently leverage multi-view, calibrated and localized input. This makes them brittle and prone to fail on dynamic egocentric captures. We propose LAMP (Localization Aware Multi-camera People Tracking): a novel, simple framework to solve this via early disentanglement of observer and target motion. LAMP introduces a two-step process. First, we leverage the known device 6 DoF motion and calibration to convert detected 2D body keypoints from all cameras over a temporal window into a unified 3D world reference frame. Second, an end-to-end-trained spatio-temporal transformer fits 3D human motion directly to this 3D ray cloud. This "lift-then-fit" approach allows LAMP to learn and leverage a natural human motion prior in the world-space, as well as providing an elegant framework to flexibly incorporate information from multiple temporally asynchronous, partially observing and moving cameras. LAMP achieves state-of-the-art results on monocular benchmarks, while significantly outperforming baselines for our targeted egocentric setting.

2026-05-06T19:23:22Z CVPR 2026. Project page: https://facebookresearch.github.io/LAMP Nan Yang Julian Straub Fan Zhang Richard Newcombe Jakob Engel Lingni Ma http://arxiv.org/abs/2605.04728v1 2026-05-06T10:23:10Z

Recovering 3D human pose and shape from a single image remains a cornerstone of human-centric vision, yet most methods assume adult subjects and optimize each person independently. These assumptions fail in real-world, all-age scenes, where body proportions and depth must be resolved jointly. We introduce Anny-Fit, a multi-person, camera-space optimization framework for all-age 3D human mesh recovery (HMR). Unlike existing per-person fitting methods, Anny-Fit jointly optimizes all individuals directly in the camera coordinate system, enforcing global spatial consistency. At the core of our approach is the use of multiple forms of expert knowledge -- including metric depth maps, instance segmentation, 2D keypoints, and, VLM-derived semantic attributes such as age and gender -- each obtained from dedicated off-the-shelf networks. These complementary signals jointly guide the optimization, constraining the depth-scale ambiguity characteristic of all-age scenes. Across diverse datasets, Anny-Fit consistently improves 2D reprojection accuracy (+13 to 16), relative depth ordering (+6 to 7), 3D estimation error (-9 to -29) and shape estimation (+25 to +82), producing more coherent scenes. Finally, we show that VLM-based semantic knowledge can be distilled into an HMR model via the pseudo-ground-truth annotations produced by Anny-Fit on training data, enabling it to learn semantically meaningful shape parameters while improving HMR performance. Our approach bridges adult-only and all-age modeling by enabling zero-shot adaptation of adult-trained HMR pipelines to the full age spectrum without retraining. Code is publicly available at https://github.com/naver/anny-fit.

2026-05-06T10:23:10Z CVPR 2026 Findings Track - Code available at https://github.com/naver/anny-fit Laura Bravo-Sánchez Matthieu Armando Romain Brégier Grégory Rogez Serena Yeung-Levy Fabien Baradel http://arxiv.org/abs/2605.04675v1 2026-05-06T09:24:37Z

Visible-thermal (RGB-T) object detection is a crucial technology for applications such as autonomous driving, where multimodal fusion enhances performance in challenging conditions like low light. However, the security of RGB-T detectors, particularly in the physical world, has been largely overlooked. This paper proposes a novel approach to RGB-T physical attacks using adversarial clothing with a non-overlapping RGB-T pattern (NORP). To simulate full-view (0$^{\circ}$--360$^{\circ}$) RGB-T attacks, we construct 3D RGB-T models for human and adversarial clothing. NORP is a new adversarial pattern design using distinct visible and thermal materials without overlap, avoiding the light reduction in overlapping RGB-T patterns (ORP). To optimize the NORP on adversarial clothing, we propose a spatial discrete-continuous optimization (SDCO) method. We systematically evaluated our method on RGB-T detectors with different fusion architectures, demonstrating high attack success rates both in the digital and physical worlds. Additionally, we introduce a fusion-stage ensemble method that enhances the transferability of adversarial attacks across unseen RGB-T detectors with different fusion architectures.

2026-05-06T09:24:37Z CVPR 2026 Xiaopei Zhu Guanning Zeng Zhanhao Hu Jun Zhu Xiaolin Hu http://arxiv.org/abs/2605.02834v2 2026-05-05T09:59:53Z

Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessential task for video understanding. Unfortunately, due to a lack of sufficiently diverse and challenging data, modern vision-language models (VLMs) are no longer evaluated on their action recognition capabilities. To revitalize action recognition in the era of VLMs, we advocate for a returned focus on domain-specific actions. To this end, we introduce VideoNet, a domain-specific action recognition benchmark covering 1,000 distinct actions from 37 domains. We begin with a multiple-choice evaluation setting, where the difference between closed and open models is stark: Gemini 3.1 Pro attains 69.9% accuracy while Qwen3-VL-8B gets a mere 45.0%. To understand why VLMs struggle on VideoNet, we relax the questions into a binary setting, where random chance is 50%. Still, Qwen achieves only 59.2% accuracy. Further relaxing the evaluation setup, we provide $k\in\{1,2,3\}$ in-context examples of the action. Some models excel in the few-shot setting, while others falter; Qwen improves $+7.0\%$, while Gemini declines $-4.8\%$. Notably, these gains fall short of the $+13.6\%$ improvement in non-expert humans when given few-shot examples. Finding that VLMs struggle to fully exploit in-context examples, we shift from test-time improvements to the training side. We collect the first large-scale training dataset for domain-specific actions, totaling nearly 500k video question-answer pairs. Fine-tuning a Molmo2-4B model on our data, we surpass all open-weight 8B models on the VideoNet benchmark.

2026-05-04T17:11:16Z CVPR 2026 Highlight. Website at https://tanu.sh/videonet Tanush Yadav Mohammadreza Salehi Jae Sung Park Vivek Ramanujan Hannaneh Hajishirzi Yejin Choi Ali Farhadi Rohun Tripathi Ranjay Krishna http://arxiv.org/abs/2605.02130v1 2026-05-04T01:19:36Z

Human-level agentic intelligence extends beyond low-level geometric perception, evolving from recognizing where things are to understanding what they are for. While existing benchmarks effectively evaluate the geometric perception capabilities of multimodal large language models (MLLMs), they fall short of probing the higher-order cognitive abilities required for grounded intelligence. To address this gap, we introduce the Spatial-Functional Intelligence Benchmark (SFI-Bench), a video-based benchmark with over 1,500 expert-annotated questions derived from diverse egocentric indoor video scans. SFI-Bench systematically evaluates two complementary dimensions of advanced reasoning: (1) Structured Spatial Reasoning, which requires understanding complex layouts and forming coherent spatial representations, and (2) Functional Reasoning, which involves inferring object affordances and their context-dependent utility. The benchmark includes tasks such as conditional counting, multi-hop relational reasoning, functional pairing, and knowledge-grounded troubleshooting, directly challenging models to integrate perception, memory, and inference. Our experiments reveal that current MLLMs consistently struggle to combine spatial memory with functional reasoning and external knowledge, highlighting a critical bottleneck in achieving grounded intelligence. SFI-Bench therefore provides a diagnostic tool for measuring progress toward more cognitively capable and truly grounded multimodal agents.

2026-05-04T01:19:36Z CVPR 2026 Le Zhang Jihan Yang Soundarya Krishnan Jimit Majmudar Xiou Ge Prasoon Puri Prathamesh Nandkishor Saraf Shruti Bhargava Dhivya Piraviperumal Yinan Ling Cindy Pan Hong Yu Aishwarya Agrawal Bo-Hsiang Tseng http://arxiv.org/abs/2605.01854v1 2026-05-03T12:51:05Z

We propose a method to reconstruct high-fidelity human avatars from multi-view video that can run on mobile devices. Many works can model high-quality Gaussian-based full-body avatars from multi-view video. However, these methods require heavy computation to obtain pose-dependent appearance, making deployment on mobile devices very difficult. Recent methods distill from pretrained models and model pose-dependent nonlinear Gaussian attributes by linearly combining global pose features with blendshapes. Although they can run on mobile devices, they suffer some loss of detail. We observe that nearby Gaussians are often highly correlated within a local region of the body, and can be linearly modeled with less error. Therefore, we use local linear blendshapes in small body parts to capture global nonlinear changes of Gaussian attributes. To further reduce computation and model size, we propose to remove blendshapes for Gaussians whose attributes change little, yielding a minimal blendshape representation. Our method is an end-to-end training method without a pretrained model. To make it run on multiple devices, we implement our method using WebGPU. Experiments show that our method can render high-quality human avatars with better details, and can reach 120 FPS at 2K resolution on mobile devices.

2026-05-03T12:51:05Z CVPR 2026. Project page https://gapszju.github.io/webavatar/ Youyi Zhan He Wang Tianjia Shao Kun Zhou http://arxiv.org/abs/2605.01657v1 2026-05-03T00:52:51Z

Vision-Language Models (VLMs) typically rely on static initial frames for video reasoning, restricting their ability to incorporate essential dynamic information as the reasoning process evolves. Existing methods that augment Chain-of-Thought (CoT) with additional frame information often exhibit suboptimal CoT quality and lack the crucial ability to synthesize visual information for hypothetical or counterfactual scenarios. We introduce Act-to-See (Act2See), a novel framework that enables active visual perception by empowering VLMs to actively interleave video frames within text CoTs. Act2See is developed via Supervised Fine-Tuning (SFT) on a high-quality dataset of reasoning traces generated by a frontier VLM. These traces integrate active calls to either retrieve existing frames or generate new ones, and are rigorously verified against human-annotated CoTs to ensure quality. This approach cultivates an emergent capability: at inference time, the model actively determines when to search for or synthesize the necessary visual evidence. Act2See establishes new state-of-the-art results on challenging benchmarks, including VideoEspresso and ViTIB, and outperforms comparable or larger models on Video-MME, EgoNormia, and VCR-Bench, demonstrating an advancement in enabling VLMs with active visual perception for video reasoning.

2026-05-03T00:52:51Z CVPR 2026 Martin Q. Ma Yuxiao Qu Aditya Agrawal Willis Guo Paul Pu Liang Ruslan Salakhutdinov Louis-Philippe Morency http://arxiv.org/abs/2604.28169v1 2026-04-30T17:53:03Z

Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a framework that introduces continuous, interpretable, and physically grounded control into video generation. Our approach integrates three key components: (i) a large-scale dataset of over 100K photorealistic simulation videos where friction, restitution, deformation, and force are systematically varied across diverse scenarios; (ii) physics-supervised fine-tuning of a pretrained diffusion model using a ControlNet conditioned on pixel-aligned physical property maps; and (iii) VLM-guided reward optimization, where a fine-tuned vision-language model evaluates generated videos with targeted physics queries and provides differentiable feedback. This combination enables a generative model to produce physically consistent and controllable outputs through variations in physical attributes-without any simulator or geometry reconstruction at inference. On the Physics-IQ benchmark, PhyCo significantly improves physical realism over strong baselines, and human studies confirm clearer and more faithful control over physical attributes. Our results demonstrate a scalable path toward physically consistent, controllable generative video models that generalize beyond synthetic training environments.

2026-04-30T17:53:03Z CVPR 2026. Project Page: https://phyco-video.github.io/ Sriram Narayanan Ziyu Jiang Srinivasa Narasimhan Manmohan Chandraker http://arxiv.org/abs/2604.28025v1 2026-04-30T15:42:17Z

Single-image human mesh recovery provides a compact 3D, person-centric representation that supports analysis, animation, AR and VR, rehabilitation, and human-computer interaction. However, prevailing systems impose an intact-limb prior and degrade on people with limb loss, because fixed-topology models cannot represent residual limbs. In this work, we present ResiHMR, a residual-limb aware framework for single-image 3D human modeling. ResiHMR adopts residual-limb keypoints and introduces two components: (i) a topology-adaptive Residual Anchor-Factor Optimization module that constrains estimation to the observed kinematic subgraph of anatomically valid structures, and (ii) a geometry-based Residual-Limb Reconstruction module that estimates residual-limb boundaries and convex limb-termination geometry. These components introduce topology-aware optimization and explicit termination geometry as tools for human mesh recovery under non-standard limb anatomy. Unlike joint-removal methods in a fixed topology, ResiHMR explicitly reconstructs residual-limb surfaces and aligns optimization with limb-loss topology, which better matches prosthetic biomechanics and real-world use. To the best of our knowledge, this is the first single-image HMR system that explicitly reconstructs residual-limb surfaces and performs topology-adaptive optimization for individuals with limb loss. On a curated dataset of real-world images with limb loss, ResiHMR improves reconstruction quality under both SMPLify-X and HSMR backbones, reducing intact-joint 2D MPJPE from 41.32 to 37.40 with SMPLify-X and residual-limb 2D MPJPE from 73.61 to 23.19 with HSMR.

2026-04-30T15:42:17Z Highlight in CVPR 2026. Project at https://akitaraphael.github.io/ResiHMR/ Jiaying Ying Heming Du Kaihao Zhang Sean M. Tweedy Xin Yu http://arxiv.org/abs/2604.27504v1 2026-04-30T06:54:35Z

Recent generative models have shown strong performance in generating diverse 3D assets from 2D images, a fundamental research topic in computer vision and graphics. However, these models still struggle to generate voluminous 3D assets when the input is a flat image that provides limited 3D cues. We introduce REVIVE 3D, a two-stage, plug-and-play pipeline for generating voluminous 3D assets from flat images. In Stage 1, we construct an Inflated Prior by inflating the foreground silhouette to recover global volume and superimposing part-aware details to capture local structure. In Stage 2, 3D Latent Refinement injects Gaussian noise into the Inflated Prior's latent and then denoises it, using the prior's geometric cues to leverage the backbone's pretrained 3D knowledge. Furthermore, our framework supports image-conditioned 3D editing. To quantify volume and surface flatness, we propose Compactness and Normal Anisotropy. We validate Compactness and Normal Anisotropy through a user study, showing that these metrics align with human perception of volume and quality. We show that REVIVE 3D achieves state-of-the-art performance on a challenging flat image dataset, based on extensive qualitative and quantitative evaluations.

2026-04-30T06:54:35Z Accepted by CVPR 2026 Hankyeol Lee Wooyeol Baek Seongdo Kim Jongyoo Kim http://arxiv.org/abs/2604.26262v3 2026-05-28T20:02:20Z

Modern scene reconstruction methods, such as 3D Gaussian Splatting, deliver photo-realistic novel view synthesis at real-time speeds, yet their adoption in interactive graphics applications has been limited. A major bottleneck is the difficulty of interacting with these representations compared to traditional, human-authored 3D assets. While previous research has attempted to impose semantic decomposition on these models, significant challenges remain regarding segmentation quality and consistency. To address this, we introduce Semantic Foam, extending the recently proposed Radiant Foam representations to semantic decomposition tasks. Our approach integrates the natural spatial volumetric decomposition of Radiant Foam's Voronoi mesh with an explicit semantic feature field parameterized at the cell level. This explicit structure enables direct spatial regularization, which prevents artifacts caused by occlusion or inconsistent supervision across views - common pitfalls for other point-based representations. Experimental results show that our method achieves comparable or superior object-level segmentation performance compared to state-of-the-art methods like Gaussian Grouping and SAGA.

2026-04-29T03:40:13Z 15 pages, 10 figures, Accepted to CVPR 2026 (Highlight) , Project page: http://semanticfoam.github.io/ Amr Sharafeldin Shrisudhan Govindarajan Thomas Walker Aryan Mikaeili Daniel Rebain Kwang Moo Yi Andrea Tagliasacchi http://arxiv.org/abs/2604.25466v1 2026-04-28T10:12:28Z

Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined structural representations to accurately position 3D Gaussians. Although these approaches have shown the remarkable progress in this field, they still suffer from inconsistent feature representations across multi-view inputs due to complex articulations of the human body and limited overlaps between different views. To address this problem, we propose a novel method to accurately localize 3D Gaussians and ultimately improve the quality of human rendering. The key idea is to unproject latent embeddings encoded from each viewpoint into a shared 3D space through predicted depth maps and recalibrate them belonging to the same body part based on cross-view attention. This helps the model resolve the spatial ambiguity occurring in highly textured regions as well as occluded body parts, thus leading to the accurate localization of 3D Gaussians. Experimental results on benchmark datasets show that the proposed method efficiently improves the performance of generalizable human Gaussian splatting from sparse-view inputs.

2026-04-28T10:12:28Z 10 pages, 8 figures, CVPR 2026 Findings Jingi Kim Wonjun Kim http://arxiv.org/abs/2604.24893v1 2026-04-27T18:19:58Z

In episodic memory with natural language queries (EM-NLQ), a user may ask a question (e.g., "Where did I place the mug?") that requires searching a long egocentric video, captured from the user's perspective, to find the moment that answers it. However, queries can be ambiguous or incomplete, leading to incorrect responses. Current methods ignore this key aspect and address EM-NLQ in a one-shot setup, limiting their applicability in real-world scenarios. In this work, we address this gap and introduce the Episodic Memory with Questions and Feedback task (EM-QnF). Here, the user can provide feedback on the model's initial prediction or add more information (e.g., "Before this. I'm looking for the big blue mug not the white one"), helping the model refine its predictions interactively. To this end, we collect datasets for feedback-based interaction and propose a lightweight training scheme that avoids expensive sequential optimization. We also introduce a plug-and-play Feedback ALignment Module (FALM) that enables existing EM-NLQ models to incorporate user feedback effectively. Our approach significantly improves over the state of the art on three challenging benchmarks and is better than or competitive with commercial large vision-language models while remaining efficient. Evaluation with human-generated feedback shows that it generalizes well to real-world scenarios.

2026-04-27T18:19:58Z Accepted to CVPR 2026. Project Page: https://nsubedi11.github.io/refocus Nikesh Subedi Loris Bazzani Ziad Al-Halah http://arxiv.org/abs/2604.23803v1 2026-04-26T16:58:19Z

Egocentric video provides a unique view into human perception and interaction, with growing relevance for augmented reality, robotics, and assistive technologies. However, rapid camera motion and complex scene dynamics pose major challenges for 3D reconstruction from this perspective. While 3D Gaussian Splatting (3DGS) has become a state-of-the-art method for efficient, high-quality novel view synthesis, variants, that focus on reconstructing dynamic scenes from monocular video are rarely evaluated on egocentric video. It remains unclear whether existing models generalize to this setting or if egocentric-specific solutions are needed. In this work, we evaluate dynamic monocular 3DGS models on egocentric and exocentric video using paired ego-exo recordings from the EgoExo4D dataset. We find that reconstruction quality is consistently lower in egocentric views. Analysis reveals that the difference in reconstruction quality, measured in peak signal-to-noise ratio, stems from the reconstruction of static, not dynamic, content. Our findings underscore current limitations and motivate the development of egocentric-specific approaches, while also highlighting the value of separately evaluating static and dynamic regions of a video.

2026-04-26T16:58:19Z Accepted at the EgoVis Workshop at CVPR 2026 Jan Warchocki Xi Wang Jonas Kulhanek Jan van Gemert http://arxiv.org/abs/2604.23264v1 2026-04-25T12:16:37Z

Text-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text while remaining physically plausible and rich in fine-grained detail. Although recent approaches can produce complex and natural movements, they usually operate at only one temporal scale, which limits both semantic alignment and temporal coherence. Inspired by the fact that complex motions are conceptualized hierarchically rather than at a single temporal scale in the human cognitive system, we propose \textit{MotionHiFlow}, a hierarchical flow matching framework to generate motion progressively by constructing flow path from low to high temporal scales. The flows at lower scales capture high-level semantics and coarse motion structures, while flows at higher scales refine temporal details. To link the flows across scales, we introduce a novel cross-scale transition process, ensuring continuity and preserving noise consistency. Furthermore, by integrating a Text-Motion Diffusion Transformer and a topology-aware Motion VAE, MotionHiFlow explicitly models structural dependencies among joints via joint-aware positional encoding and skeletal topology, enabling precise semantic alignment alongside fine-grained motion details. Extensive experiments on HumanML3D and KIT-ML benchmarks demonstrate state-of-the-art performance, with ablation studies confirming the effectiveness of the hierarchical design and key components. Code is available at https://github.com/ai-lh/MotionHiFlow.

2026-04-25T12:16:37Z accepted to CVPR 2026 Heng Li Xiaotong Lin Ling-An Zeng Yulei Kang Shuai Li Jian-Fang Hu http://arxiv.org/abs/2604.22984v1 2026-04-24T19:55:51Z

We train a language model to generate LEGO-brick build sequences. While prior work has been restricted to discrete, voxel-like towers, we consider a much broader set of pieces, encompassing thousands of part types with diverse connection semantics. To enable this, we first collect a large-scale dataset of over 100,000 human-designed LDraw brick objects and scenes. The complexity of our setting makes it challenging to autoregressively assemble structures that satisfy physical constraints. When predicting block pose directly, build sequences quickly become invalid after a small number of steps. Although pieces are placed in 3D space, it is the spatial relationships of the parts which define the whole. With this in mind, we design a graph-based program representation that parametrizes structure through connectivity, improving the physical grounding of generated sequences. To enable future applications, we make our dataset and models available for research purposes. https://kulits.github.io/BrickNet

2026-04-24T19:55:51Z CVPR 2026; project page: https://kulits.github.io/BrickNet Peter Kulits Cordelia Schmid http://arxiv.org/abs/2604.22160v2 2026-06-26T16:26:41Z

Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation. Humans robustly detect and segment moving entities that constitute independently moveable chunks of matter, whether observing sparse moving dots, textured surfaces, or naturalistic scenes. In contrast, existing computer vision systems lack a unified approach that works across these diverse settings. Inspired by principles of human perception, we propose a generative model that hierarchically groups low-level motion cues and high-level appearance features into particles (small Gaussians representing local matter), and groups particles into clusters capturing coherently and independently moveable physical entities. We develop a hardware-accelerated inference algorithm based on parallelized block Gibbs sampling to recover stable particle motion and groupings. Our model operates on different kinds of inputs (random dots, stylized textures, or naturalistic RGB video), enabling it to work across settings where biological vision succeeds but existing computer vision approaches do not. We validate this unified framework across three domains: on 2D random dot kinematograms, our approach captures human object perception including graded uncertainty across ambiguous conditions; on a Gestalt-inspired dataset of camouflaged rotating objects, our approach recovers correct 3D structure from motion and thereby accurate 2D object segmentation; and on naturalistic RGB videos, our model tracks the moving 3D matter that makes up deforming objects, enabling robust object-level scene understanding. This work thus establishes a general framework for motion-based perception grounded in principles of human vision.

2026-04-24T02:18:18Z 25 pages, 12 figures, CVPR 2026 Eric Li Arijit Dasgupta Yoni Friedman Mathieu Huot Vikash Mansinghka Thomas O'Connell William T. Freeman Joshua B. Tenenbaum http://arxiv.org/abs/2604.22865v1 2026-04-23T09:01:27Z

We introduce MeshLAM, a feed-forward framework for one-shot animatable mesh head reconstruction that generates high-fidelity, animatable 3D head avatars from a single image. Unlike previous work that relies on time-consuming test-time optimization or extensive multi-view data, our method produces complete mesh representations with inherent animatability from a single image in a single forward pass. Our approach employs a dual shape and texture map architecture that simultaneously processes mesh vertices and texture map with extracted image features from a shared transformer backbone, allowing for coherent shape carving and appearance modeling. To prevent mesh collapse and ensure topological integrity during feed-forward deformation, we propose an iterative GRU-based decoding mechanism with progressive geometry deformation and texture refinement, coupled with a novel reprojection-based texture guidance mechanism that anchors appearance learning to the input image. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in reconstruction quality, animation capability, and computational efficiency. Project page at https://meshlam.github.io.

2026-04-23T09:01:27Z Accepted to CVPR 2026 Yisheng He Steven Hoi http://arxiv.org/abs/2604.21119v1 2026-04-22T22:04:35Z

Rings like gold, thuds like wood! The sound we hear in a scene is shaped not only by the spatial layout of the environment but also by the materials of the objects and surfaces within it. For instance, a room with wooden walls will produce a different acoustic experience from a room with the same spatial layout but concrete walls. Accurately modeling these effects is essential for applications such as virtual reality, robotics, architectural design, and audio engineering. Yet, existing methods for acoustic modeling often entangle spatial and material influences in correlated representations, which limits user control and reduces the realism of the generated acoustics. In this work, we present a novel approach for material-controlled Room Impulse Response (RIR) generation that explicitly disentangles the effects of spatial and material cues in a scene. Our approach models the RIR using two modules: a spatial module that captures the influence of the spatial layout of the scene, and a material module that modulates this spatial RIR according to a user-specified material configuration. This explicitly disentangled design allows users to easily modify the material configuration of a scene and observe its impact on acoustics without altering the spatial structure or scene content. Our model provides significant improvements over prior approaches on both acoustic-based metrics (up to +16% on RTE) and material-based metrics (up to +70%). Furthermore, through a human perceptual study, we demonstrate the improved realism and material sensitivity of our model compared to the strongest baselines.

2026-04-22T22:04:35Z Accepted to CVPR 2026 Findings. Project page: https://mahnoor-fatima-saad.github.io/MatRIR.html Mahnoor Fatima Saad Sagnik Majumder Kristen Grauman Ziad Al-Halah http://arxiv.org/abs/2604.20715v1 2026-04-22T16:01:04Z

Relighting a person from a single photo is an attractive but ill-posed task, as a 2D image ambiguously entangles 3D geometry, intrinsic appearance, and illumination. Current methods either use sequential pipelines that suffer from error accumulation, or they do not explicitly leverage 3D geometry during relighting, which limits physical consistency. Since relighting and estimation of 3D geometry are mutually beneficial tasks, we propose a unified Multi-Modal Diffusion Transformer (DiT) that jointly solves for both: GeoRelight. We make this possible through two key technical contributions: isotropic NDC-Orthographic Depth (iNOD), a distortion-free 3D representation compatible with latent diffusion models; and a strategic mixed-data training method that combines synthetic and auto-labeled real data. By solving geometry and relighting jointly, GeoRelight achieves better performance than both sequential models and previous systems that ignored geometry.

2026-04-22T16:01:04Z CVPR 2026 Highlight; Project page: https://yuxuan-xue.com Yuxuan Xue Ruofan Liang Egor Zakharov Timur Bagautdinov Chen Cao Giljoo Nam Shunsuke Saito Gerard Pons-Moll Javier Romero http://arxiv.org/abs/2604.21718v2 2026-04-26T23:28:29Z

Video-language models (VLMs) learn to reason about the dynamic visual world through natural language. We introduce a suite of open datasets, benchmarks, and recipes for scalable oversight that enable precise video captioning. First, we define a structured specification for describing subjects, scenes, motion, spatial, and camera dynamics, grounded by hundreds of carefully defined visual primitives developed with professional video creators such as filmmakers. Next, to curate high-quality captions, we introduce CHAI (Critique-based Human-AI Oversight), a framework where trained experts critique and revise model-generated pre-captions into improved post-captions. This division of labor improves annotation accuracy and efficiency by offloading text generation to models, allowing humans to better focus on verification. Additionally, these critiques and preferences between pre- and post-captions provide rich supervision for improving open-source models (Qwen3-VL) on caption generation, reward modeling, and critique generation through SFT, DPO, and inference-time scaling. Our ablations show that critique quality in precision, recall, and constructiveness, ensured by our oversight framework, directly governs downstream performance. With modest expert supervision, the resulting model outperforms closed-source models such as Gemini-3.1-Pro. Finally, we apply our approach to re-caption large-scale professional videos (e.g., films, commercials, games) and fine-tune video generation models such as Wan to better follow detailed prompts of up to 400 words, achieving finer control over cinematography including camera motion, angle, lens, focus, point of view, and framing. Our results show that precise specification and human-AI oversight are key to professional-level video understanding and generation. Data and code are available on our project page: https://linzhiqiu.github.io/papers/chai/

2026-04-22T09:01:04Z CVPR 2026 Highlight. Project page: https://linzhiqiu.github.io/papers/chai/ Zhiqiu Lin Chancharik Mitra Siyuan Cen Isaac Li Yuhan Huang Yu Tong Tiffany Ling Hewei Wang Irene Pi Shihang Zhu Ryan Rao George Liu Jiaxi Li Ruojin Li Yili Han Yilun Du Deva Ramanan http://arxiv.org/abs/2604.20336v1 2026-04-22T08:31:40Z

Co-manipulation requires multiple humans to synchronize their motions with a shared object while ensuring reasonable interactions, maintaining natural poses, and preserving stable states. However, most existing motion generation approaches are designed for single-character scenarios or fail to account for payload-induced dynamics. In this work, we propose a flow-matching framework that ensures the generated co-manipulation motions align with the intended goals while maintaining naturalness and effectiveness. Specifically, we first introduce a generative model that derives explicit manipulation strategies from the object's affordance and spatial configuration, which guide the motion flow toward successful manipulation. To improve motion quality, we then design an adversarial interaction prior that promotes natural individual poses and realistic inter-person interactions during co-manipulation. In addition, we also incorporate a stability-driven simulation into the flow matching process, which refines unstable interaction states through sampling-based optimization and directly adjusts the vector field regression to promote more effective manipulation. The experimental results demonstrate that our method achieves higher contact accuracy, lower penetration, and better distributional fidelity compared to state-of-the-art human-object interaction baselines. The code is available at https://github.com/boycehbz/StaCOM.

2026-04-22T08:31:40Z CVPR 2026 Jiahao Xu Xiaohan Yuan Xingchen Wu Chongyang Xu Kun Li Buzhen Huang http://arxiv.org/abs/2604.20286v1 2026-04-22T07:33:14Z

Recent segmentation models have demonstrated promising efficiency by aggressively reducing parameter counts and computational complexity. However, these models often struggle to accurately delineate fine lesion boundaries and texture patterns essential for early skin cancer diagnosis and treatment planning. In this paper, we propose MambaLiteUNet, a compact yet robust segmentation framework that integrates Mamba state space modeling into a U-Net architecture, along with three key modules: Adaptive Multi-Branch Mamba Feature Fusion (AMF), Local-Global Feature Mixing (LGFM), and Cross-Gated Attention (CGA). These modules are designed to enhance local-global feature interaction, preserve spatial details, and improve the quality of skip connections. MambaLiteUNet achieves an average IoU of 87.12% and average Dice score of 93.09% across ISIC2017, ISIC2018, HAM10000, and PH2 benchmarks, outperforming state-of-the-art models. Compared to U-Net, our model improves average IoU and Dice by 7.72 and 4.61 points, respectively, while reducing parameters by 93.6% and GFLOPs by 97.6%. Additionally, in domain generalization with six unseen lesion categories, MambaLiteUNet achieves 77.61% IoU and 87.23% Dice, performing best among all evaluated models. Our extensive experiments demonstrate that MambaLiteUNet achieves a strong balance between accuracy and efficiency, making it a competitive and practical solution for dermatological image segmentation. Our code is publicly available at: https://github.com/maklachur/MambaLiteUNet.

2026-04-22T07:33:14Z Accepted at CVPR 2026 Main Md Maklachur Rahman Soon Ki Jung Tracy Hammond http://arxiv.org/abs/2604.17818v1 2026-04-20T05:15:38Z

Reconstructing 3D human motion and human-object interactions (HOI) from Internet videos is a fundamental step toward building large-scale datasets of human behavior. Existing methods struggle to recover globally consistent 3D motion under dynamic cameras, especially for motion types underrepresented in current motion-capture datasets, and face additional difficulty recovering coherent human-object interactions in 3D. We introduce a two-stage framework leveraging 2D diffusion that reconstructs 3D human motion and HOI from Internet videos. In the first stage, we synthesize multi-view 2D motion data for each domain, leveraging 2D keypoints extracted from Internet videos to incorporate human motions that rarely appear in existing MoCap datasets. In the second stage, a camera-conditioned multi-view 2D motion diffusion model is trained on the domain-specific synthetic data to recover 3D human motion and 3D HOI in the world space. We demonstrate the effectiveness of our method on Internet videos featuring challenging motions such as gymnastics, as well as in-the-wild HOI videos, and show that it outperforms prior work in producing realistic human motion and human-object interaction.

2026-04-20T05:15:38Z CVPR 2026. Project website: https://awfuact.github.io/anylift/ The first two authors contribute equally Hongjie Li Heng Yu Jiaman Li Hong-Xing Yu Ehsan Adeli C. Karen Liu Jiajun Wu http://arxiv.org/abs/2604.17190v1 2026-04-19T01:36:53Z

Aerial Vision-and-Language Navigation (Aerial VLN) enables unmanned aerial vehicles (UAVs) to follow natural language instructions and navigate complex urban environments. While recent advances have achieved progress through large-scale memory graphs and lookahead path planning, they remain limited by shallow instruction understanding and high computational cost. In particular, existing methods rely primarily on landmark descriptions, overlooking directional cues "a key source of spatial context in human navigation". In this work, we propose LookasideVLN, a new paradigm that exploits directional cues in natural language to achieve both more accurate spatial reasoning and greater computational efficiency. LookasideVLN comprises three core components: (1) an Egocentric Lookaside Graph (ELG) that dynamically encodes instruction-relevant landmarks and their directional relationships, (2) a Spatial Landmark Knowledge Base (SLKB) that provides lightweight memory retrieval from prior navigation experiences, and (3) a Lookaside MLLM Navigation Agent that aligns multimodal information from user instructions, visual observations, and landmark-direction information from ELG for path planning. Extensive experiments show that LookasideVLN significantly outperforms the state-of-the-art CityNavAgent, even with a single-level lookahead, demonstrating that leveraging directional cues is a powerful yet efficient strategy for Aerial VLN.

2026-04-19T01:36:53Z Accepted by CVPR 2026 Yuwei Ning Ganlong Zhao Yipeng Qin Si Liu Yang Liu Liang Lin Guanbin Li http://arxiv.org/abs/2604.16298v1 2026-04-17T17:59:48Z

UAV vision-language navigation (VLN) requires an agent to navigate complex 3D environments from an egocentric perspective while following ambiguous multi-step instructions over long horizons. Existing zero-shot methods remain limited, as they often rely on large base models, generic prompts, and loosely coordinated modules. In this work, we propose FineCog-Nav, a top-down framework inspired by human cognition that organizes navigation into fine-grained modules for language processing, perception, attention, memory, imagination, reasoning, and decision-making. Each module is driven by a moderate-sized foundation model with role-specific prompts and structured input-output protocols, enabling effective collaboration and improved interpretability. To support fine-grained evaluation, we construct AerialVLN-Fine, a curated benchmark of 300 trajectories derived from AerialVLN, with sentence-level instruction-trajectory alignment and refined instructions containing explicit visual endpoints and landmark references. Experiments show that FineCog-Nav consistently outperforms zero-shot baselines in instruction adherence, long-horizon planning, and generalization to unseen environments. These results suggest the effectiveness of fine-grained cognitive modularization for zero-shot aerial navigation. Project page: https://smartdianlab.github.io/projects-FineCogNav.

2026-04-17T17:59:48Z Accepted by CVPR 2026 Findings Dian Shao Zhengzheng Xu Peiyang Wang Like Liu Yule Wang Jieqi Shi Jing Huo http://arxiv.org/abs/2604.16010v1 2026-04-17T12:33:45Z

This paper proposes image-adaptive contrast limited adaptive histogram equalization (IA-CLAHE). Conventional CLAHE is widely used to boost the performance of various computer vision tasks and to improve visual quality for human perception in practical industrial applications. CLAHE applies contrast limited histogram equalization to each local region to enhance local contrast. However, CLAHE often leads to over-enhancement, because the contrast-limiting parameter clip limit is fixed regardless of the histogram distribution of each local region. Our IA-CLAHE addresses this limitation by adaptively estimating tile-wise clip limits from the input image. To achieve this, we train a lightweight clip limits estimator with a differentiable extension of CLAHE, enabling end-to-end optimization. Unlike prior learning-based CLAHE methods, IA-CLAHE does not require pre-searched ground-truth clip limits or task-specific datasets, because it learns to map input image histograms toward a domain-invariant uniform distribution, enabling zero-shot generalization across diverse conditions. Experimental results show that IA-CLAHE consistently improves recognition performance, while simultaneously enhancing visual quality for human perception, without requiring any task-specific training data.

2026-04-17T12:33:45Z Accepted to NTIRE 2026 Workshop at CVPR 2026 Rikuto Otsuka Yuho Shoji Yuka Ogino Takahiro Toizumi Atsushi Ito http://arxiv.org/abs/2604.15311v3 2026-09-05T11:59:09Z

This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differentiable generation process of flow matching. However, backpropagating through long trajectories results in prohibitive memory costs and gradient explosion. Therefore, direct-gradient methods struggle to update early generation steps, which are crucial for determining the global structure of the final image. To address this issue, we introduce LeapAlign, a fine-tuning method that reduces computational cost and enables direct gradient propagation from reward to early generation steps. Specifically, we shorten the long trajectory into only two steps by designing two consecutive leaps, each skipping multiple ODE sampling steps and predicting future latents in a single step. By randomizing the start and end timesteps of the leaps, LeapAlign leads to efficient and stable model updates at any generation step. To better use such shortened trajectories, we assign higher training weights to those that are more consistent with the long generation path. To further enhance gradient stability, we reduce the weights of gradient terms with large magnitude, instead of completely removing them as done in previous works. When fine-tuning the Flux model, LeapAlign consistently outperforms state-of-the-art GRPO-based and direct-gradient methods across various metrics, achieving superior image quality and image-text alignment.

2026-04-16T17:59:56Z Accepted by CVPR 2026. Project page: https://rockeycoss.github.io/leapalign/ Zhanhao Liang Tao Yang Jie Wu Chengjian Feng Liang Zheng http://arxiv.org/abs/2604.15310v2 2026-04-17T17:17:33Z

This paper presents a method for image relighting that enables precise and continuous control over multiple illumination attributes in a photograph. We formulate relighting as a conditional image generation task and introduce attribute tokens to encode distinct lighting factors such as intensity, color, ambient illumination, diffuse level, and 3D light positions. The model is trained on a large-scale synthetic dataset with ground-truth lighting annotations, supplemented by a small set of real captures to enhance realism and generalization. We validate our approach across a variety of relighting tasks, including controlling in-scene lighting fixtures and editing environment illumination using virtual light sources, on synthetic and real images. Our method achieves state-of-the-art quantitative and qualitative performance compared to prior work. Remarkably, without explicit inverse rendering supervision, the model exhibits an inherent understanding of how light interacts with scene geometry, occlusion, and materials, yielding convincing lighting effects even in traditionally challenging scenarios such as placing lights within objects or relighting transparent materials plausibly. Project page: vrroom.github.io/tokenlight/

2026-04-16T17:59:50Z 32 pages, CVPR 2026, Project Page: https://vrroom.github.io/tokenlight/ Sumit Chaturvedi Yannick Hold-Geoffroy Mengwei Ren Jingyuan Liu He Zhang Yiqun Mei Julie Dorsey Zhixin Shu http://arxiv.org/abs/2604.14762v1 2026-04-16T08:22:09Z

Generalized Category Discovery (GCD) challenges methods to identify known and novel classes using partially labeled data, mirroring human category learning. Unlike prior GCD methods, which operate within a single modality and require dataset-specific fine-tuning, we propose a modality-agnostic GCD approach inspired by the human brain's abstract category formation. Our $\textbf{OmniGCD}$ leverages modality-specific encoders (e.g., vision, audio, text, remote sensing) to process inputs, followed by dimension reduction to construct a $\textbf{GCD latent space}$, which is transformed at test-time into a representation better suited for clustering using a novel synthetically trained Transformer-based model. To evaluate OmniGCD, we introduce a $\textbf{zero-shot GCD setting}$ where no dataset-specific fine-tuning is allowed, enabling modality-agnostic category discovery. $\textbf{Trained once on synthetic data}$, OmniGCD performs zero-shot GCD across 16 datasets spanning four modalities, improving classification accuracy for known and novel classes over baselines (average percentage point improvement of $\textbf{+6.2}$, $\textbf{+17.9}$, $\textbf{+1.5}$ and $\textbf{+12.7}$ for vision, text, audio and remote sensing). This highlights the importance of strong encoders while decoupling representation learning from category discovery. Improving modality-agnostic methods will propagate across modalities, enabling encoder development independent of GCD. Our work serves as a benchmark for future modality-agnostic GCD works, paving the way for scalable, human-inspired category discovery. All code is available $\href{https://github.com/Jordan-HS/OmniGCD}{here}$

2026-04-16T08:22:09Z Accepted to CVPR 2026 Findings Jordan Shipard Arnold Wiliem Kien Nguyen Thanh Wei Xiang Clinton Fookes http://arxiv.org/abs/2604.13448v1 2026-04-15T04:01:23Z

Human-object interaction (HOI) detection aims to detect interactions between humans and objects in images. While recent advances have improved performance on existing benchmarks, their evaluations mainly focus on overall prediction accuracy and provide limited insight into the underlying causes of model failures. In particular, modern models often struggle in complex scenes involving multiple people and rare interaction combinations. In this work, we present a study to better understand the failure modes of two-stage HOI models, which form the basis of many current HOI detection approaches. Rather than constructing a large-scale benchmark, we instead decompose HOI detection into multiple interpretable perspectives and analyze model behavior across these dimensions to study different types of failure patterns. We curate a subset of images from an existing HOI dataset organized by human-object-interaction configurations (e.g., multi-person interactions and object sharing), and analyze model behavior under these configurations to examine different failure modes. This design allows us to analyze how these HOI models behave under different scene compositions and why their predictions fail. Importantly, high overall benchmark performance does not necessarily reflect robust visual reasoning about human-object relationships. We hope that this study can provide useful insights into the limitations of HOI models and offer observations for future research in this area.

2026-04-15T04:01:23Z Accepted to SAUAFG Workshop at CVPR 2026 Lemeng Wang Qinqian Lei Vidhi Bakshi Daniel Yi Yifan Liu Jiacheng Hou Asher Seng Hao Zheda Mai Wei-Lun Chao Robby T. Tan Bo Wang http://arxiv.org/abs/2604.13305v1 2026-04-14T21:20:47Z

Reward models (RMs) are inherently non-neutral value functions designed and trained to encode specific objectives, such as human preferences or text-image alignment. RMs have become crucial components of text-to-image (T2I) generation systems where they are used at various stages for dataset filtering, as evaluation metrics, as a supervisory signal during optimization of parameters, and for post-generation safety and quality filtering of T2I outputs. While specific problems with the integration of RMs into the T2I pipeline have been studied (e.g. reward hacking or mode collapse), their robustness and fairness as scoring functions remains largely unknown. We conduct a large scale audit of RM robustness with respect to demographic biases during T2I model training and generation. We provide quantitative and qualitative evidence that while originally developed as quality measures, RMs encode demographic biases, which cause reward-guided optimization to disproportionately sexualize female image subjects reinforce gender/racial stereotypes, and collapse demographic diversity. These findings highlight shortcomings in current reward models, challenge their reliability as quality metrics, and underscore the need for improved data collection and training procedures to enable more robust scoring.

2026-04-14T21:20:47Z Accepted to The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026 Salma Abdel Magid Grace Guo Esin Tureci Amaya Dharmasiri Vikram V. Ramaswamy Hanspeter Pfister Olga Russakovsky http://arxiv.org/abs/2604.12894v1 2026-04-14T15:42:48Z

We present CUBE (Control-based Unified B-spline Encoding), a new geometric representation for human faces that combines B-spline volumes with learned features, and demonstrate its use as a decoder for 3D scan registration and monocular 3D face reconstruction. Unlike existing B-spline representations with 3D control points, CUBE is parametrized by a lattice (e.g., 8 x 8 x 8) of high-dimensional control features, increasing the model's expressivity. These features define a continuous, two-stage mapping from a 3D parametric domain to 3D Euclidean space via an intermediate feature space. First, high-dimensional control features are locally blended using the B-spline bases, yielding a high-dimensional feature vector whose first three values define a 3D base mesh. A small MLP then processes this feature vector to predict a residual displacement from the base shape, yielding the final refined 3D coordinates. To reconstruct 3D surfaces in dense semantic correspondence, CUBE is queried at 3D coordinates sampled from a fixed template mesh. Crucially, CUBE retains the local support property of traditional B-spline representations, enabling local surface editing by updating individual control features. We demonstrate the strengths of this representation by training transformer-based encoders to predict CUBE's control features from unstructured point clouds and monocular images, achieving state-of-the-art scan registration results compared to recent baselines.

2026-04-14T15:42:48Z Accepted to CVPR 2026 (Highlight) Prashanth Chandran Daoye Wang Timo Bolkart http://arxiv.org/abs/2604.12803v1 2026-04-14T14:33:28Z

Neuromorphic vision sensors offer low latency and high dynamic range, but their deployment in public spaces raises severe data protection concerns. Recent Event-to-Video (E2V) models can reconstruct high-fidelity intensity images from sparse event streams, inadvertently exposing human identities. Current obfuscation methods, such as masking or scrambling, corrupt the spatio-temporal structure, severely degrading data utility for downstream perception tasks. In this paper, to the best of our knowledge, we present the first generative anonymization framework for event streams to resolve this utility-privacy trade-off. By bridging the modality gap between asynchronous events and standard spatial generative models, our pipeline projects events into an intermediate intensity representation, leverages pretrained models to synthesize realistic, non-existent identities, and re-encodes the features back into the neuromorphic domain. Experiments demonstrate that our method reliably prevents identity recovery from E2V reconstructions while preserving the structural data integrity required for downstream vision tasks. Finally, to facilitate rigorous evaluation, we introduce a novel, synchronized real-world event and RGB dataset captured via precise robotic trajectories, providing a robust benchmark for future research in privacy-preserving neuromorphic vision.

2026-04-14T14:33:28Z Accepted to the 1st Workshop on Low-Level Vision Frontiers (LoViF) at IEEE/CVF CVPR 2026 Adam T. Müller Mihai Kocsis Nicolaj C. Stache http://arxiv.org/abs/2604.12765v1 2026-04-14T14:06:43Z

Marker-based motion capture (MoCap) systems have long been the gold standard for accurate 4D human modeling, yet their reliance on specialized hardware and markers limits scalability and real-world deployment. Advancing reliable markerless 4D human motion capture requires datasets that reflect the complexity of real-world human interactions. Yet, existing benchmarks often lack realistic multi-person dynamics, severe occlusions, and challenging interaction patterns, leading to a persistent domain gap. In this work, we present a new dataset and evaluation for complex 4D markerless human motion capture. Our proposed MoCap dataset captures both single and multi-person scenarios with intricate motions, frequent inter-person occlusions, rapid position exchanges between similarly dressed subjects, and varying subject distances. It includes synchronized multi-view RGB and depth sequences, accurate camera calibration, ground-truth 3D motion capture from a Vicon system, and corresponding SMPL/SMPL-X parameters. This setup ensures precise alignment between visual observations and motion ground truth. Benchmarking state-of-the-art markerless MoCap models reveals substantial performance degradation under these realistic conditions, highlighting limitations of current approaches. We further demonstrate that targeted fine-tuning improves generalization, validating the dataset's realism and value for model development. Our evaluation exposes critical gaps in existing models and provides a rigorous foundation for advancing robust markerless 4D human motion capture.

2026-04-14T14:06:43Z 14 pages, 11 figures, 4 tables. Accepted for publication at CVPR 2026 4D World Models Workshop Yeeun Park Miqdad Naduthodi Suryansh Kumar http://arxiv.org/abs/2604.12518v2 2026-04-19T08:18:31Z

Multimodal sentiment analysis (MSA) integrates heterogeneous text, audio, and visual signals to infer human emotions. While recent approaches leverage cross-modal complementarity, they often struggle to fully utilize weaker modalities. In practice, dominant modalities tend to overshadow non-verbal ones, inducing modality competition and limiting overall contributions. This imbalance degrades fusion performance and robustness under noisy or missing modalities. To address this, we propose a novel model, Enhance-then-Balance Modality Collaboration framework (EBMC). EBMC improves representation quality via semantic disentanglement and cross-modal enhancement, strengthening weaker modalities. To prevent dominant modalities from overwhelming others, an Energy-guided Modality Coordination mechanism achieves implicit gradient rebalancing via a differentiable equilibrium objective. Furthermore, Instance-aware Modality Trust Distillation estimates sample-level reliability to adaptively modulate fusion weights, ensuring robustness. Extensive experiments demonstrate that EBMC achieves state-of-the-art or competitive results and maintains strong performance under missing-modality settings.

2026-04-14T09:52:53Z Accepted by CVPR 2026 Kang He Yuzhe Ding Xinrong Wang Fei Li Chong Teng Donghong Ji http://arxiv.org/abs/2604.11961v1 2026-04-13T18:52:12Z

Gait assessment is a key clinical indicator of fall risk and overall health in older adults. However, standard clinical practice is largely limited to stopwatch-measured gait speed. We present a pipeline that leverages a 3D Human Mesh Recovery (HMR) model to extract gait parameters from recordings of older adults completing the Timed Up and Go (TUG) test. From videos recorded across different community centers, we extract and analyze spatiotemporal gait parameters, including step time, sit-to-stand duration, and step length. We found that video-derived step time was significantly correlated with IMU-based insole measurements. Using linear mixed effects models, we confirmed that shorter, more variable step lengths and longer sit-to-stand durations were predicted by higher self-rated fall risk and fear of falling. These findings demonstrate that our pipeline can enable accessible and ecologically valid gait analysis in community settings.

2026-04-13T18:52:12Z Work was accepted at Computer Vision for Biomechanics Workshop (CVBW) at CVPR 2026 Chitra Banarjee Patrick Kwon Ania Lipat Rui Xie Chen Chen Ladda Thiamwong http://arxiv.org/abs/2604.11539v2 2026-07-07T14:40:30Z

Human perception of visual similarity is inherently adaptive and subjective, depending on the users' interests and focus. However, most image retrieval systems fail to reflect this flexibility, relying on a fixed, monolithic metric that cannot incorporate multiple conditions simultaneously. To address this, we propose CLAY, an adaptive similarity computation method that reframes the embedding space of pretrained Vision-Language Models (VLMs) as a text-conditional similarity space without additional training. This design separates the textual conditioning process and visual feature extraction, allowing highly efficient and multi-conditioned retrieval with fixed visual embeddings. We also construct a synthetic evaluation dataset CLAY-EVAL, for comprehensive assessment under diverse conditioned retrieval settings. Experiments on standard datasets and our proposed dataset show that CLAY achieves high retrieval accuracy and notable computational efficiency compared to previous works.

2026-04-13T14:33:13Z CVPR 2026, Project page: https://sohwi-lim.github.io/CLAY Sohwi Lim Lee Hyoseok Jungjoon Park Tae-Hyun Oh http://arxiv.org/abs/2604.11156v1 2026-04-13T08:17:56Z

Unsupervised remote photoplethysmography (rPPG) promises to leverage unlabeled video data, but its potential is hindered by a critical challenge: training on low-quality "in-the-wild" videos severely degrades model performance. An essential step missing here is to assess the suitability of the videos for rPPG model learning before using them for the task. Existing video quality assessment (VQA) methods are mainly designed for human perception and not directly applicable to the above purpose. In this work, we propose rPPG-VQA, a novel framework for assessing video suitability for rPPG. We integrate signal-level and scene-level analyses and design a dual-branch assessment architecture. The signal-level branch evaluates the physiological signal quality of the videos via robust signal-to-noise ratio (SNR) estimation with a multi-method consensus mechanism, and the scene-level branch uses a multimodal large language model (MLLM) to identify interferences like motion and unstable lighting. Furthermore, we propose a two-stage adaptive sampling (TAS) strategy that utilizes the quality score to curate optimal training datasets. Experiments show that by training on large-scale, "in-the-wild" videos filtered by our framework, we can develop unsupervised rPPG models that achieve a substantial improvement in accuracy on standard benchmarks. Our code is available at https://github.com/Tianyang-Dai/rPPG-VQA.

2026-04-13T08:17:56Z Accepted by CVPR 2026 Tianyang Dai Ming Chang Yan Chen Yang Hu http://arxiv.org/abs/2604.10485v1 2026-04-12T06:37:01Z

Low-visibility scenarios, such as low-light conditions, pose significant challenges to human pose estimation due to the scarcity of annotated low-light datasets and the loss of visual information under poor illumination. Recent domain adaptation techniques attempt to utilize well-lit labels by augmenting well-lit images to mimic low-light conditions. But handcrafted augmentations oversimplify noise patterns, while learning-based methods often fail to preserve high-frequency low-light characteristics, producing unrealistic images that lead pose models to generalize poorly to real low-light scenes. Moreover, recent pose estimators rely on image cues through image-to-keypoint cross-attention, but these cues become unreliable under low-light conditions. To address these issues, we propose Unsupervised Domain Adaptation for Pose Estimation (UDAPose), a novel framework that synthesizes low-light images and dynamically fuses visual cues with pose priors for improved pose estimation. Specifically, our synthesis method incorporates a Direct-Current-based High-Pass Filter (DHF) and a Low-light Characteristics Injection Module (LCIM) to inject high-frequency details from input low-light images, overcoming rigidity or the detail loss in existing approaches. Furthermore, we introduce a Dynamic Control of Attention (DCA) module that adaptively balances image cues with learned pose priors in the Transformer architecture. Experiments show that UDAPose outperforms state-of-the-art methods, with notable AP gains of 10.1 (56.4%) on the ExLPose-test hard set (LL-H) and 7.4 (31.4%) in cross-dataset validation on EHPT-XC. Code: https://github.com/Vision-and-Multimodal-Intelligence-Lab/UDAPose

2026-04-12T06:37:01Z Accepted at CVPR 2026 Haopeng Chen Yihao Ai Kabeen Kim Robby T. Tan Yixin Chen Bo Wang http://arxiv.org/abs/2604.10127v1 2026-04-11T09:44:39Z

The rapid advancement of AIGC-based video generation has underscored the critical need for comprehensive evaluation frameworks that go beyond traditional generation quality metrics to encompass aesthetic appeal. However, existing benchmarks remain largely focused on technical fidelity, leaving a significant gap in holistic assessment-particularly with respect to perceptual and artistic qualities. To address this limitation, we introduce VGA-Bench, a unified benchmark for joint evaluation of video generation quality and aesthetic quality. VGA-Bench is built upon a principled three-tier taxonomy: Aesthetic Quality, Aesthetic Tagging, and Generation Quality, each decomposed into multiple fine-grained sub-dimensions to enable systematic assessment. Guided by this taxonomy, we design 1,016 diverse prompts and generate a large-scale dataset of over 60,000 videos using 12 video generation models, ensuring broad coverage across content, style, and artifacts. To enable scalable and automated evaluation, we annotate a subset of the dataset via human labeling and develop three dedicated multi-task neural assessors: VAQA-Net for aesthetic quality prediction, VTag-Net for automatic aesthetic tagging, and VGQA-Net for generation and basic quality attributes. Extensive experiments demonstrate that our models achieve reliable alignment with human judgments, offering both accuracy and efficiency. We release VGA-Bench as a public benchmark to foster research in AIGC evaluation, with applications in content moderation, model debugging, and generative model optimization.

2026-04-11T09:44:39Z CVPR 2026 Longteng Jiang DanDan Zheng Qianqian Qiao Heng Huang Huaye Wang Yihang Bo Bao Peng Jingdong Chen Jun Zhou Xin Jin http://arxiv.org/abs/2604.09853v2 2026-04-14T17:35:03Z

Understanding human motion processing is essential for building reliable, human-centered computer vision systems. Although deep neural networks (DNNs) achieve strong performance in optical flow estimation, they remain less robust than humans and rely on fundamentally different computational strategies. Visual motion illusions provide a powerful probe into these mechanisms, revealing how human and machine vision align or diverge. While recent DNN-based motion models can reproduce dynamic illusions such as reverse-phi, it remains unclear whether they can perceive illusory motion in static images, exemplified by the Rotating Snakes illusion. We evaluate several representative optical flow models on Rotating Snakes and show that most fail to generate flow fields consistent with human perception. Under simulated conditions mimicking saccadic eye movements, only the human-inspired Dual-Channel model exhibits the expected rotational motion, with the closest correspondence emerging during the saccade simulation. Ablation analyses further reveal that both luminance-based and higher-order color--feature--based motion signals contribute to this behavior and that a recurrent attention mechanism is critical for integrating local cues. Our results highlight a substantial gap between current optical-flow models and human visual motion processing, and offer insights for developing future motion-estimation systems with improved correspondence to human perception and human-centric AI.

2026-04-10T19:33:33Z Accepted to CVPR 2026 Findings Isabella Elaine Rosario Columbia University Fan L. Cheng Columbia University Zitang Sun Kyoto University Nikolaus Kriegeskorte Columbia University http://arxiv.org/abs/2604.09817v1 2026-04-10T18:49:44Z

Visual encoding and decoding models act as gateways to understanding the neural mechanisms underlying human visual perception. Typically, visual encoding models that predict brain activity from stimuli and decoding models that reproduce stimuli from brain activity are treated as distinct tasks, requiring separate models and training procedures. This separation is inefficient and fails to model the consistency between encoding and decoding processes. To address this limitation, we propose NeuroFlow, the first unified framework that jointly models visual encoding and decoding from neural activity within a single flow model. NeuroFlow introduces two key components: (1) NeuroVAE is designed as a variational backbone to model neural variability and establish a compact, semantically structured latent space for bidirectional modeling across visual and neural modalities. (2) Cross-modal Flow Matching (XFM) bypasses the typical paradigm of noise-to-data diffusion guided by a specific modality condition, instead learning a reversibly consistent flow model between visual and neural latent distributions. For the first time, visual encoding and decoding are reformulated as a time-dependent, reversible process within a shared latent space for unified modeling. Empirical results demonstrate that NeuroFlow achieves superior overall performance in visual encoding and decoding tasks with higher computational efficiency compared to any isolated methods. We further analyze principal factors that steer the model toward encoding-decoding consistency and, through brain functional analyses, demonstrate that NeuroFlow captures consistent activation patterns underlying neural variability. NeuroFlow marks a major step toward unified visual encoding and decoding from neural activity, providing mechanistic insights that inform future bidirectional visual brain-computer interfaces.

2026-04-10T18:49:44Z Accepted to CVPR 2026. Project page: https://michaelmaiii.github.io/NeuroFlow-S Weijian Mai Mu Nan Yu Zhu Jiahang Cao Rui Zhang Yuqin Dai Chunfeng Song Andrew F. Luo Jiamin Wu http://arxiv.org/abs/2604.09367v2 2026-05-27T14:52:01Z

Ancient inscriptions, as repositories of cultural memory, have suffered from centuries of environmental and human-induced degradation. Restoring their intertwined visual and textual integrity poses one of the most demanding challenges in digital heritage preservation. However, existing AI-based approaches often rely on rigid pipelines, struggling to generalize across such complex and heterogeneous real-world degradations. Inspired by the skill-coordinated workflow of human epigraphers, we propose EpiAgent, an agent-centric system that formulates inscription restoration as a hierarchical planning problem. Following an Observe-Conceive-Execute-Reevaluate paradigm, an LLM-based central planner orchestrates collaboration among multimodal analysis, historical experience, specialized restoration tools, and iterative self-refinement. This agent-centric coordination enables a flexible and adaptive restoration process beyond conventional single-pass methods. Across real-world degraded inscriptions, EpiAgent achieves superior restoration quality and stronger generalization compared to existing methods. Our work marks an important step toward expert-level agent-driven restoration of cultural heritage. The code is available at https://github.com/blackprotoss/EpiAgent.

2026-04-10T14:37:54Z Accepted by CVPR 2026 Shipeng Zhu Ang Chen Na Nie Pengfei Fang Min-Ling Zhang Hui Xue http://arxiv.org/abs/2604.13098v1 2026-04-10T06:11:35Z

State-of-the-art (SOTA) urban traffic control increasingly employs Multi-Agent Reinforcement Learning (MARL) to coordinate Traffic Light Controllers (TLCs) and Connected Autonomous Vehicles (CAVs). However, the performance of these systems is fundamentally capped by their hand-crafted, myopic rewards (e.g., intersection pressure), which fail to capture high-level, human-centric goals like safety, flow stability, and comfort. To overcome this limitation, we introduce C2T, a novel framework that learns a common-sense coordination model from traffic-vehicle dynamics. C2T distills "common-sense" knowledge from a Large Language Model (LLM) into a learned intrinsic reward function. This new reward is then used to guide the coordination policy of a cooperative multi-intersection TLC MARL system on CityFlow-based multi-intersection benchmarks. Our framework significantly outperforms strong MARL baselines in traffic efficiency, safety, and an energy-related proxy. We further highlight C2T's flexibility in principle, allowing distinct "efficiency-focused" versus "safety-focused" policies by modifying the LLM prompt.

2026-04-10T06:11:35Z Accepted to CVPR 2026 Findings Track Yuyang Chen Kaiyan Zhao Yiming Wang Ming Yang Bin Rao Zhenning Li http://arxiv.org/abs/2604.08836v1 2026-04-10T00:25:41Z

Generative object compositing methods have shown remarkable ability to seamlessly insert objects into scenes. However, when applied to real-world catalog image generation, these methods require tedious manual intervention: users must carefully adjust masks when product dimensions differ, and painstakingly restore occluded elements post-generation. We present CatalogStitch, a set of model-agnostic techniques that automate these corrections, enabling user-friendly content creation. Our dimension-aware mask computation algorithm automatically adapts the target region to accommodate products with different dimensions; users simply provide a product image and background, without manual mask adjustments. Our occlusion-aware hybrid restoration method guarantees pixel-perfect preservation of occluding elements, eliminating post-editing workflows. We additionally introduce CatalogStitch-Eval, a 58-example benchmark covering aspect-ratio mismatch and occlusion-heavy catalog scenarios, together with supplementary PDF and HTML viewers. We evaluate our techniques with three state-of-the-art compositing models (ObjectStitch, OmniPaint, and InsertAnything), demonstrating consistent improvements across diverse catalog scenarios. By reducing manual intervention and automating tedious corrections, our approach transforms generative compositing into a practical, human-friendly tool for production catalog workflows.

2026-04-10T00:25:41Z CVPR 2026 HiGen Workshop. Project page, https://catalogstitch.github.io Sanyam Jain Pragya Kandari Manit Singhal He Zhang Soo Ye Kim http://arxiv.org/abs/2604.08543v1 2026-04-09T17:59:52Z

Event cameras offer multiple advantages in monocular egocentric 3D human pose estimation from head-mounted devices, such as millisecond temporal resolution, high dynamic range, and negligible motion blur. Existing methods effectively leverage these properties, but suffer from low 3D estimation accuracy, insufficient in many applications (e.g., immersive VR/AR). This is due to the design not being fully tailored towards event streams (e.g., their asynchronous and continuous nature), leading to high sensitivity to self-occlusions and temporal jitter in the estimates. This paper rethinks the setting and introduces E-3DPSM, an event-driven continuous pose state machine for event-based egocentric 3D human pose estimation. E-3DPSM aligns continuous human motion with fine-grained event dynamics; it evolves latent states and predicts continuous changes in 3D joint positions associated with observed events, which are fused with direct 3D human pose predictions, leading to stable and drift-free final 3D pose reconstructions. E-3DPSM runs in real-time at 80 Hz on a single workstation and sets a new state of the art in experiments on two benchmarks, improving accuracy by up to 19% (MPJPE) and temporal stability by up to 2.7x. See our project page for the source code and trained models.

2026-04-09T17:59:52Z 20 pages; 14 figures and 14 tables; CVPR 2026; project page: https://4dqv.mpi-inf.mpg.de/E-3DPSM/ Mayur Deshmukh Hiroyasu Akada Helge Rhodin Christian Theobalt Vladislav Golyanik http://arxiv.org/abs/2604.08536v1 2026-04-09T17:59:19Z

We introduce RewardFlow, an inversion-free framework that steers pretrained diffusion and flow-matching models at inference time through multi-reward Langevin dynamics. RewardFlow unifies complementary differentiable rewards for semantic alignment, perceptual fidelity, localized grounding, object consistency, and human preference, and further introduces a differentiable VQA-based reward that provides fine-grained semantic supervision through language-vision reasoning. To coordinate these heterogeneous objectives, we design a prompt-aware adaptive policy that extracts semantic primitives from the instruction, infers edit intent, and dynamically modulates reward weights and step sizes throughout sampling. Across several image editing and compositional generation benchmarks, RewardFlow delivers state-of-the-art edit fidelity and compositional alignment.

2026-04-09T17:59:19Z CVPR 2026. Project page: https://plan-lab.github.io/rewardflow Onkar Susladkar Dong-Hwan Jang Tushar Prakash Adheesh Juvekar Vedant Shah Ayush Barik Nabeel Bashir Muntasir Wahed Ritish Shrirao Ismini Lourentzou http://arxiv.org/abs/2604.07193v1 2026-04-08T15:18:39Z

Predicting affect in unconstrained environments remains a fundamental challenge in human-centered AI. While deep neural embeddings dominate contemporary approaches, they often lack interpretability and limit expert-driven refinement. We propose a novel framework that uses Language Models (LMs) as semantic context conditioners over handcrafted affect descriptors to model changes in Valence and Arousal. Our approach begins with interpretable facial geometry and acoustic features derived from structured domain knowledge. These features are transformed into symbolic natural-language descriptions encoding their affective implications. A pretrained LM processes these descriptions to generate semantic context embeddings that act as high-level priors over affective dynamics. Unlike end-to-end black-box pipelines, our framework preserves feature transparency while leveraging the contextual abstraction capabilities of LMs. We evaluate the proposed method on the Aff-Wild2 and SEWA datasets for affect change prediction. Experimental results show consistent improvements in accuracy for both Valence and Arousal compared to handcrafted-only and deep-embedding baselines. Our findings demonstrate that semantic conditioning enables interpretable affect modelling without sacrificing predictive performance, offering a transparent and computationally efficient alternative to fully end-to-end architectures

2026-04-08T15:18:39Z This paper has been accepted at the CVPR 2026 Workshop on Affective Behavior Analysis in-the-wild (ABAW) Kosmas Pinitas Ilias Maglogiannis http://arxiv.org/abs/2604.07166v1 2026-04-08T14:55:36Z

Although visual foundation models like DINOv2 provide state-of-the-art performance as feature extractors, their complex, high-dimensional representations create substantial hurdles for interpretability. This work proposes DINO-QPM, which converts these powerful but entangled features into contrastive, class-independent representations that are interpretable by humans. DINO-QPM is a lightweight interpretability adapter that pursues globally interpretable image classification, adapting the Quadratic Programming Enhanced Model (QPM) to operate on strictly frozen DINO backbones. While classification with visual foundation models typically relies on the \texttt{CLS} token, we deliberately diverge from this standard. By leveraging average-pooling, we directly connect the patch embeddings to the model's features and therefore enable spatial localisation of DINO-QPM's globally interpretable features within the input space. Furthermore, we apply a sparsity loss to minimise spatial scatter and background noise, ensuring that explanations are grounded in relevant object parts. With DINO-QPM we make the level of interpretability of QPM available as an adapter while exceeding the accuracy of DINOv2 linear probe. Evaluated through an introduced Plausibility metric and other interpretability metrics, extensive experiments demonstrate that DINO-QPM is superior to other applicable methods for frozen visual foundation models in both classification accuracy and explanation quality.

2026-04-08T14:55:36Z Accepted to the 5th Explainable AI for Computer Vision (XAI4CV) Workshop at CVPR 2026 Robert Zimmermann Thomas Norrenbrock Bodo Rosenhahn http://arxiv.org/abs/2604.07132v1 2026-04-08T14:26:52Z

Child Sexual Abuse Imagery (CSAI) classification is an important yet challenging problem for computer vision research due to the strict legal and ethical restrictions that prevent the public sharing of CSAI datasets. This limitation hinders reproducibility and slows progress in developing automated methods. In this work, we introduce CSA-Graphs, a privacy-preserving structural dataset. Instead of releasing the original images, we provide structural representations that remove explicit visual content while preserving contextual information. CSA-Graphs includes two complementary graph-based modalities: scene graphs describing object relationships and skeleton graphs encoding human pose. Experiments show that both representations retain useful information for classifying CSAI, and that combining them further improves performance. This dataset enables broader research on computer vision methods for child safety while respecting legal and ethical constraints.

2026-04-08T14:26:52Z Conference on Computer Vision and Pattern Recognition (CVPR 2026), in the Workshop on Computer Vision for Children (CV4CHL) Carlos Caetano Camila Laranjeira Clara Ernesto Artur Barros João Macedo Leo S. F. Ribeiro Jefersson A. dos Santos Sandra Avila http://arxiv.org/abs/2604.06824v1 2026-04-08T08:40:33Z

Sound source localization task aims to identify the locations of sound-emitting objects by leveraging correlations between audio and visual modalities. Most existing SSL methods rely on contrastive learning-based feature matching, but lack explicit reasoning and verification, limiting their effectiveness in complex acoustic scenes. Inspired by human meta-cognitive processes, we propose a training-free SSL framework that exploits the intrinsic reasoning capabilities of Multimodal Large Language Models (MLLMs). Our Generation-Analysis-Refinement (GAR) pipeline consists of three stages: Generation produces initial bounding boxes and audio classifications; Analysis quantifies Audio-Visual Consistency via open-set role tagging and anchor voting; and Refinement applies adaptive gating to prevent unnecessary adjustments. Extensive experiments on single-source and multi-source benchmarks demonstrate competitive performance. The source code is available at https://github.com/VisualAIKHU/GAR-SSL.

2026-04-08T08:40:33Z Accepted to CVPR 2026 Subin Park Jung Uk Kim http://arxiv.org/abs/2604.06467v1 2026-04-07T21:09:52Z

Realistic digital avatars require expressive and dynamic hair motion; however, most existing head avatar methods assume rigid hair movement. These methods often fail to disentangle hair from the head, representing it as a simple outer shell and failing to capture its natural volumetric behavior. In this paper, we address these limitations by introducing PhysHead, a hybrid representation for animatable head avatars with realistic hair dynamics learned from multi-view video. At the core is a 3D Gaussian-based layered representation of the head. Our approach combines a 3D parametric mesh for the head with strand-based hair, which can be directly simulated using physics engines. For the appearance model, we employ Gaussian primitives attached to both the head mesh and hair segments. This representation enables the creation of photorealistic head avatars with dynamic hair behavior, such as wind-blown motion, overcoming the constraints of rigid hair in existing methods. However, these animation capabilities also require new training schemes. In particular, we propose the use of VLM-based models to generate appearance of regions that are occluded in the dynamic training sequences. In quantitative and qualitative studies, we demonstrate the capabilities of the proposed model and compare it with existing baselines. We show that our method can synthesize physically plausible hair motion besides expression and camera control.

2026-04-07T21:09:52Z Project Page: see https://phys-head.github.io/; Youtube Video: see https://www.youtube.com/watch?v=k68fsSSwzc0; Accepted to CVPR 2026 Berna Kabadayi Vanessa Sklyarova Wojciech Zielonka Justus Thies Gerard Pons-Moll http://arxiv.org/abs/2604.05621v2 2026-04-26T16:43:43Z

We present FunRec, a method for reconstructing functional 3D digital twins of indoor scenes directly from egocentric RGB-D interaction videos. Unlike existing methods on articulated reconstruction, which rely on controlled setups, multi-state captures, or CAD priors, FunRec operates directly on in-the-wild human interaction sequences to recover interactable 3D scenes. It automatically discovers articulated parts, estimates their kinematic parameters, tracks their 3D motion, and reconstructs static and moving geometry in canonical space, yielding simulation-compatible meshes. Across new real and simulated benchmarks, FunRec surpasses prior work by a large margin, achieving up to +50 mIoU improvement in part segmentation, 5-10 times lower articulation and pose errors, and significantly higher reconstruction accuracy. We further demonstrate applications on URDF/USD export for simulation, hand-guided affordance mapping and robot-scene interaction.

2026-04-07T09:22:12Z CVPR 2026. Project page: https://functionalscenes.github.io Alexandros Delitzas Chenyangguang Zhang Alexey Gavryushin Tommaso Di Mario Boyang Sun Rishabh Dabral Leonidas Guibas Christian Theobalt Marc Pollefeys Francis Engelmann Daniel Barath http://arxiv.org/abs/2604.05584v2 2026-04-08T06:36:00Z

Robust multimodal human sensing must overcome the critical challenge of missing modalities. Two principal barriers are the Representation Gap between heterogeneous data and the Contamination Effect from low-quality modalities. These barriers are causally linked, as the corruption introduced by contamination fundamentally impedes the reduction of representation disparities. In this paper, we propose PTA, a novel "Purify-then-Align" framework that solves this causal dependency through a synergistic integration of meta-learning and knowledge diffusion. To purify the knowledge source, PTA first employs a meta-learning-driven weighting mechanism that dynamically learns to down-weight the influence of noisy, low-contributing modalities. Subsequently, to align different modalities, PTA introduces a diffusion-based knowledge distillation paradigm in which an information-rich clean teacher, formed from this purified consensus, refines the features of each student modality. The ultimate payoff of this "Purify-then-Align" strategy is the creation of exceptionally powerful single-modality encoders imbued with cross-modal knowledge. Comprehensive experiments on the large-scale MM-Fi and XRF55 datasets, under pronounced Representation Gap and Contamination Effect, demonstrate that PTA achieves state-of-the-art performance and significantly improves the robustness of single-modality models in diverse missing-modality scenarios.

2026-04-07T08:24:47Z Accepted by CVPR 2026 Workshop On Any-to-Any Multimodal Learning Pengcheng Weng Yanyu Qian Yangxin Xu Fei Wang http://arxiv.org/abs/2604.05510v2 2026-04-12T18:17:34Z

Augmented reality (AR) has rapidly expanded over the past decade. As AR becomes increasingly integrated into daily life, its security and reliability emerge as critical challenges. Among various threats, contradictory virtual content attacks, where malicious or inconsistent virtual elements are introduced into the user's view, pose a unique risk by misleading users, creating semantic confusion, or delivering harmful information. In this work, we systematically model such attacks and present ContrAR, a novel benchmark for evaluating the robustness of vision-language models (VLMs) against virtual content manipulation and contradiction in AR. ContrAR contains 312 real-world AR videos validated by 10 human participants. We further benchmark 11 VLMs, including both commercial and open-source models. Experimental results reveal that while current VLMs exhibit reasonable understanding of contradictory virtual content, room still remains for improvement in detecting and reasoning about adversarial content manipulations in AR environments. Moreover, balancing detection accuracy and latency remains challenging.

2026-04-07T07:04:28Z CVPR 2026 Findings Yanming Xiu Zhengyuan Jiang Neil Zhenqiang Gong Maria Gorlatova http://arxiv.org/abs/2604.05436v1 2026-04-07T05:09:41Z

Reconstructing textured 3D human models from a single image is fundamental for AR/VR and digital human applications. However, existing methods mostly focus on single individuals and thus fail in multi-human scenes, where naive composition of individual reconstructions often leads to artifacts such as unrealistic overlaps, missing geometry in occluded regions, and distorted interactions. These limitations highlight the need for approaches that incorporate group-level context and interaction priors. We introduce a holistic method that explicitly models both group- and instance-level information. To mitigate perspective-induced geometric distortions, we first transform the input into a canonical orthographic space. Our primary component, Human Group-Instance Multi-View Diffusion (HUG-MVD), then generates complete multi-view normals and images by jointly modeling individuals and group context to resolve occlusions and proximity. Subsequently, the Human Group-Instance Geometric Reconstruction (HUG-GR) module optimizes the geometry by leveraging explicit, physics-based interaction priors to enforce physical plausibility and accurately model inter-human contact. Finally, the multi-view images are fused into a high-fidelity texture. Together, these components form our complete framework, HUG3D. Extensive experiments show that HUG3D significantly outperforms both single-human and existing multi-human methods, producing physically plausible, high-fidelity 3D reconstructions of interacting people from a single image. Project page: https://jongheean11.github.io/HUG3D_project

2026-04-07T05:09:41Z Accepted to CVPR 2026 Gwanghyun Kim Junghun James Kim Suh Yoon Jeon Jason Park Se Young Chun http://arxiv.org/abs/2604.04934v2 2026-05-04T04:50:40Z

We present Vanast, a unified framework that generates garment-transferred human animation videos directly from a single human image, garment images, and a pose guidance video. Conventional two-stage pipelines treat image-based virtual try-on and pose-driven animation as separate processes, which often results in identity drift, garment distortion, and front-back inconsistency. Our model addresses these issues by performing the entire process in a single unified step to achieve coherent synthesis. To enable this setting, we construct large-scale triplet supervision. Our data generation pipeline includes generating identity-preserving human images in alternative outfits that differ from garment catalog images, capturing full upper and lower garment triplets to overcome the single-garment-posed video pair limitation, and assembling diverse in-the-wild triplets without requiring garment catalog images. We further introduce a Dual Module architecture for video diffusion transformers to stabilize training, preserve pretrained generative quality, and improve garment accuracy, pose adherence, and identity preservation while supporting zero-shot garment interpolation. Together, these contributions allow Vanast to produce high-fidelity, identity-consistent animation across a wide range of garment types.

2026-04-06T17:59:59Z Accepted to CVPR 2026 Highlight, Project Page: https://hyunsoocha.github.io/vanast/ Hyunsoo Cha Wonjung Woo Byungjun Kim Hanbyul Joo http://arxiv.org/abs/2604.04787v2 2026-04-20T16:19:39Z

We introduce AvatarPointillist, a novel framework for generating dynamic 4D Gaussian avatars from a single portrait image. At the core of our method is a decoder-only Transformer that autoregressively generates a point cloud for 3D Gaussian Splatting. This sequential approach allows for precise, adaptive construction, dynamically adjusting point density and the total number of points based on the subject's complexity. During point generation, the AR model also jointly predicts per-point binding information, enabling realistic animation. After generation, a dedicated Gaussian decoder converts the points into complete, renderable Gaussian attributes. We demonstrate that conditioning the decoder on the latent features from the AR generator enables effective interaction between stages and markedly improves fidelity. Extensive experiments validate that AvatarPointillist produces high-quality, photorealistic, and controllable avatars. We believe this autoregressive formulation represents a new paradigm for avatar generation, and we will release our code inspire future research.

2026-04-06T15:56:50Z Accepted by the CVPR 2026 main conference. Project page: https://kumapowerliu.github.io/AvatarPointillist/ Hongyu Liu Xuan Wang Zijian Wu Yating Wang Ziyu Wan Yue Ma Runtao Liu Boyao Zhou Yujun Shen Qifeng Chen http://arxiv.org/abs/2604.04500v1 2026-04-06T07:51:59Z

Vision-language models (VLMs) have achieved remarkable success across diverse tasks. However, concerns about their trustworthiness persist, particularly regarding tendencies to lean more on textual cues than visual evidence and the risk of producing ungrounded or fabricated responses. To address these issues, we propose Saliency-R1, a framework for improving the interpretability and faithfulness of VLMs reasoning. Specifically, we introduce a novel saliency map technique that efficiently highlights critical image regions contributing to generated tokens without additional computational overhead. This can further be extended to trace how visual information flows through the reasoning process to the final answers, revealing the alignment between the thinking process and the visual context. We use the overlap between the saliency maps and human-annotated bounding boxes as the reward function, and apply Group Relative Policy Optimization (GRPO) to align the salient parts and critical regions, encouraging models to focus on relevant areas when conduct reasoning. Experiments show Saliency-R1 improves reasoning faithfulness, interpretability, and overall task performance.

2026-04-06T07:51:59Z CVPR 2026 Shizhan Gong Minda Hu Qiyuan Zhang Chen Ma Qi Dou