https://arxiv.org/api/dQ9zWSSxfTqITiKLn23/UAiYo4s 2026-09-28T19:00:27Z 80 688 0 http://arxiv.org/abs/2609.22687v1 2026-09-19T01:42:19Z

We present PanoSeg3R, a feed-forward framework for 3D panoramic semantic segmentation. Unlike existing methods designed for perspective inputs, PanoSeg3R jointly predicts 3D geometry and multi-view semantic segmentation in one single forward pass. Built upon a pretrained reconstruction backbone that supports panoramic images, our approach extends feed-forward 3D reconstruction with a query-based mask decoder. Furthermore, we introduce an automatic panorama data curation pipeline that leverages the complementary strengths of off-the-shelf foundation models to generate reliable pseudo semantic annotations, substantially expanding the training data and improving zero-shot generalization. PanoSeg3R achieves state-of-the-art performance on panoramic 3D semantic segmentation, improving 3D mIoU by up to 16.02 on ScanNet++, while the curated training data further improves zero-shot performance by up to 4.26 and 43.28 mIoU on Stanford2D3D and ToF-360, respectively. Website: https://harryyoon777.github.io/PanoSeg3R/

2026-09-19T01:42:19Z Heechan Yoon Dongki Jung Phuc Nguyen Ming Lin Dinesh Manocha http://arxiv.org/abs/2609.19143v1 2026-09-16T17:59:30Z

Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded. Current vision-language models (VLMs) can generate fluent and detailed image captions, but reliably associating them with image pixels remains challenging. Existing methods that combine dense captioning with pixel-level grounding often produce either incomplete descriptions or inaccurate segmentation masks. We study this problem through panoptic grounded captioning, a task that requires a VLM to describe both foreground objects and background regions while grounding each referring phrase with pixel-level masks. We make three contributions. First, we introduce PanoCaps, a human-annotated benchmark constructed from panoptic segmentation datasets. It provides dense captions with near-complete pixel coverage and image-text alignments at the entity level, supporting both training and evaluation. We further propose a phrase-mask matching protocol and a generalized Panoptic Quality (gPQ) metric that jointly evaluates textual and mask agreement. Second, we formulate phrase grounding as selection from a phrase-conditioned pool of mask proposals and introduce PANORAMA, a VLM that conditions a pretrained segmenter on contextualized phrase representations to obtain candidate masks and learns to select those corresponding to each phrase. Training this interface jointly with caption generation enables PANORAMA to produce high-quality masks while allowing each phrase to refer to a single region or multiple instances. Third, PANORAMA achieves the best overall grounding on PanoCaps and matches or exceeds specialized models across several pixel-level grounding tasks. Experiments show that our method produces precise entity-level segmentations while maintaining detailed, mask-consistent captions. Code, data and models are available at https://www.di.ens.fr/willow/research/panorama/.

2026-09-16T17:59:30Z Sara Pieri Evangelos Kazakos Shizhe Chen Josef Sivic Cordelia Schmid http://arxiv.org/abs/2609.17800v1 2026-09-15T20:10:43Z

Vision-language models (VLMs) remain largely unreliable on panoramic dental radiographs and can rely on learned anatomical priors rather than evidence in the image. This is particularly problematic for tooth localization and spatial reasoning, and fine-tuned dental VLMs can retain the same spatial biases. We present AgenTeeth, a model-agnostic, tool-augmented framework that grounds frozen VLMs using seven specialized dental vision experts. A question-aware orchestrator selects the relevant tools, whose detections are mapped to FDI tooth numbers or anatomical regions and returned as structured findings together with annotated image overlays. A fresh synthesis call then answers the question using this evidence, without fine-tuning the underlying VLM. On MMOral-OPG-Bench, AgenTeeth improves four backbone VLMs by 12.9-23.0 percentage points over their baselines. Our strongest configuration reaches 65.66% on open-ended VQA, compared with 45.35% for OralGPT-Plus. The advantage also holds at matched scale: a frozen Qwen2.5-VL-7B-Instruct with AgenTeeth reaches 48.11%, exceeding OralGPT-Plus built on the same backbone after supervised fine-tuning and reinforcement learning for tool use. We release the framework, all seven expert models, and a dentist-annotated dataset for alveolar bone-loss detection in panoramic radiographs.

2026-09-15T20:10:43Z 10 pages, 2 figures, 5 tables Ahmed Rafid Fariya Ahmed Rumman Adib Mehedi Ahamed Ajwad Abrar Tareque Mohmud Chowdhury http://arxiv.org/abs/2609.14462v1 2026-09-13T12:13:51Z

Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity observations with low latency. Existing approaches face a representation trade-off: perspective models operate on local views and must preserve off-screen content over long rollouts, whereas broader spatial coverage is typically obtained by synthesizing full-sphere videos or constructing explicit 3D representations. Motivated by the complementary roles of global context and selective local acuity in visual perception, we present AlayaVista, a camera-controllable streaming video world model that decouples panoramic world evolution from perspective observation synthesis. Given a single perspective image, AlayaVista constructs a 360-degree scene prior using a pretrained panorama expansion model and then evolves the scene as a camera-conditioned panoramic latent state. A latent viewport renderer maps this state to the requested perspective video latents, while a perspective refiner restores details, suppresses artifacts, and performs super-resolution. To support efficient streaming, we adapt the panoramic generator to chunk-autoregressive generation and distill both panoramic generation and perspective refinement into few-step processes. To provide the supervision required by this design, we construct MUGEN, a large-scale real-world panoramic video dataset containing 1,318 hours of videos at resolutions of at least 4K, together with rich semantic and geometric annotations.

2026-09-13T12:13:51Z Project page: https://alaya-lab.github.io/AlayaVista Jiaming Tan Mingliang Zhai Zhen Li Yuwei Wu Chuanhao Li Kaipeng Zhang http://arxiv.org/abs/2609.09890v1 2026-09-09T08:46:34Z

Multi-view diffusion models have shown strong performance in scenes with strong geometric priors and sparse semantics, such as indoor rooms or simple outdoor environments (e.g., fields, courtyards). However, they often fail to maintain cross-view consistency under camera rotation, especially in structurally complex urban environments. Without explicit modeling of spherical correspondence across views, existing approaches tend to produce object duplication, structural distortion, and layout inconsistency. To address this limitation, we propose StreetDiff, a multi-view diffusion framework that explicitly enforces cross-view alignment during denoising. StreetDiff introduces a Panorama--Perspective Synergy design to decouple global layout reasoning from local detail synthesis, and incorporates a Panorama Alignment Module (PAM) that establishes spherical-projection-based attention constraints across views. By injecting structured alignment constraints without modifying the diffusion backbone, our framework achieves robust cross-view coherence in challenging urban street scene generation tasks. In addition, we construct Street360, a large-scale HDR multi-view urban panorama dataset. Extensive experiments demonstrate that StreetDiff significantly improves structural consistency and visual fidelity compared to prior multi-view diffusion generation methods.

2026-09-09T08:46:34Z 10 pages, 4 figures Qi Zhang Yanyifan Wang Weiyuan Zhang Hui Huang http://arxiv.org/abs/2609.09394v1 2026-09-08T19:45:58Z

Recovering metric 3D geometry from monocular images is a fundamental computer vision task, yet current methods remain heavily fragmented by fixed camera model assumptions and inflexible input schemes. We present OmniPoint, a unified framework designed to generalize metric reconstruction across diverse imaging sensors, including pinhole, fisheye, and equirectangular projections, while accommodating varying geometric priors. To overcome projection rigidity, OmniPoint abandons conventional planar depth regression. It instead adopts a decoupled ray and distance representation alongside a decoupled training objective, explicitly separating the camera projection model from the scene structure. To address the severe scarcity of training data for alternative cameras, we introduce a bidirectional augmentation strategy that explicitly bridges labeled perspective data and unlabeled omnidirectional domains in 3D space. Furthermore, to seamlessly integrate optional inputs like camera intrinsics or sparse depth without destabilizing the network through feature distribution shifts, we propose a robust information injection mechanism. This mechanism utilizes learnable input state embeddings to resolve architectural ambiguity and applies vectorized Gaussian smoothing to densify irregular measurements. Extensive experiments demonstrate that OmniPoint achieves state-of-the-art zero-shot performance across multiple benchmarks, establishing a robust new standard for unified monocular 3D reconstruction.

2026-09-08T19:45:58Z ECCV 20026. Project Page: https://botaoye.github.io/omnipoint/ Botao Ye Marc Pollefeys Ming-Hsuan Yang Abhijit Kundu http://arxiv.org/abs/2609.08118v1 2026-09-08T01:49:43Z

Existing image quality assessment (IQA) methods typically predict mean opinion scores (MOSs) but struggle to capture variations in individual subject behaviors. This limitation is highly pronounced in immersive visual applications such as stitched 360-degree panoramas, where user opinions diverge drastically based on personal sensitivity to blending-induced luminance inconsistency, detail loss, and geometric misalignment. Here we propose GC360IQ, a novel Generic-to-Individualized IQA framework that establishes a learned explicit feature space to characterize individual subject behaviors. First, we construct a specialized 360-degree panorama database focusing on blending-induced luminance and detail degradation while minimizing geometric misalignment, providing multidimensional quality ratings alongside complete individual scores. Second, we develop a generic quality model that utilizes unblended views as a perceptual reference. Dual feature extraction branches capture gradient and structural information specifically around stitching regions to predict baseline quality. Third, we construct a compact preference embedding space that acts as an explicit feature domain to model each subject's deviation from generic quality perceptions. We also introduce a maximum a posteriori (MAP) adaptation mechanism. By leveraging a preference prior learned within our explicit feature space, a new subject's unique behavioral embedding is mapped progressively with an increasing number of anchor ratings. Experiments demonstrate that the generic model provides accurate stitching quality predictions and that subject adaptation further improves individual score predictions. Deeper analysis of the collected ratings and learned embeddings reveals that observer differences contain structured variation related to scoring tendencies and sensitivity to stitching artifacts, rather than merely random rating noise.

2026-09-08T01:49:43Z 12 pages, 11 figures. Submitted to IEEE Transactions on Image Processing Jinghan Zhou Zhou Wang http://arxiv.org/abs/2609.06099v1 2026-09-05T13:51:48Z

Reconstructing 4D scenes from casually captured monocular video is vital for applications in virtual reality (VR) and embodied AI. Recent advances in 4D reconstruction and novel view synthesis have substantially propelled this capability. However, existing reconstruction methods generally cannot recover regions beyond visible camera limits. Consequently, we introduce a new paradigm that achieves 4D scene synthesis by combining visible-region reconstruction from monocular input with invisible-region generation beyond observable camera boundaries. We present Panoramic Alignment for Strategic Exploitation of Generative Priors (PASTEL). Specifically, PASTEL proposes panoramic scene alignment, a novel representation that reformulates the intractable 3D "invisible region" exploration into a tractable 2D directional trajectory planning. This is achieved by reducing the viewpoint planning from 6-DoF search to a 2D directional search with explicit visibility boundaries. By operating within this panoramic space, our method strategically identifies camera trajectories that maximize exploration beyond observable boundaries while minimizing viewpoint deviation. Experimental results show that PASTEL can not only extrapolate plausible scene content beyond the observable boundaries of input monocular videos, but also substantially boost monocular 4D reconstruction performance. PASTEL outperforms the previous state-of-the-art method by 0.9dB in full-image PSNR on the DyCheck IPhone dataset.

2026-09-05T13:51:48Z Accepted to ECCV 2026. 11 figures Yuankun Yang Yi Wei Bo Bai Wenyang Zhou Li Zhang http://arxiv.org/abs/2609.01997v1 2026-09-02T02:13:26Z

We propose LF-MultiDiffusion, a training-free panorama generation method that extends MultiDiffusion to support linear projections between target and reference image spaces. Our key idea is to reformulate latent aggregation as a regularized least-squares problem and solve it efficiently with a Krylov-based iterative solver inside the denoising loop. This formulation enables denser and more natural mappings than prior training-free methods, yielding more stable generation with far fewer perspective views. As a result, LF-MultiDiffusion reduces the number of image generator evaluations during denoising and significantly improves inference efficiency. Experiments show that LF-MultiDiffusion achieves better visual quality, text alignment, and panoramic consistency than the strongest training-free baseline, while providing a 15.36$\times$ speedup. Our project page is available at: https://ahykw.github.io/lfmd.

2026-09-02T02:13:26Z Accepted to ECCV 2026 Akio Hayakawa Yusuke Mukuta Tatsuya Harada http://arxiv.org/abs/2609.01479v1 2026-09-01T16:16:06Z

Beyond semantic content, camera parameters play a pivotal role in dictating the geometric perspective and appearance of any given image. While recent image editing models excel at semantic and stylistic manipulation, they struggle with explicit camera parameter control. When handling large perspective shifts, instruction-driven models face a dilemma: they either suffer from structural tearing or generate conservative outputs that ignore geometric instructions. To address this, we introduce CameraEditor, a framework that reformulates camera-controlled editing from a spatial problem into a temporal sequence prediction task. By leveraging the temporal coherence of video diffusion models, our approach integrates an explicit geometric perception module with a dynamic reference routing mechanism. This allows us to construct geometrically rigorous visual reference pairs via dynamic panorama cropping, overcoming the ambiguity of text-based instructions. Furthermore, CameraEditor strategically inserts intermediate transition frames to decompose large perspective shifts, providing a robust temporal buffer that preserves content identity and spatial coherence. We construct a training dataset of 5,760 instances. As an independent contribution, we introduce CamEditor-Bench, a model-agnostic evaluation suite of 462 test cases. Extensive experiments demonstrate that CameraEditor achieves state-of-the-art camera control precision and source identity preservation, outperforming existing methods.

2026-09-01T16:16:06Z Accepted to ACM Multimedia 2026 Xin Shen Chengyou Jia Keshuo Xing Zifeng Zhu Changliang Xia Bowen Ping Zhuohang Dang Hangwei Qian Minnan Luo 10.1145/3767308.3835398 http://arxiv.org/abs/2608.30471v1 2026-08-31T08:58:13Z

This paper investigates the problem of position estimation of unmanned surface vessels (USVs) operating in coastal areas or in the archipelago. We propose a position estimation method where the horizon line is extracted in a 360 degree panoramic image around the USV. We design a CNN architecture to determine an approximate horizon line in the image and implicitly determine the camera orientation (the pitch and roll angles). The panoramic image is warped to compensate for the camera orientation and to generate an image from an approximately level camera. A second CNN architecture is designed to extract the pixelwise horizon line in the warped image. The extracted horizon line is correlated with digital elevation model (DEM) data in the Fourier domain using a MOSSE correlation filter. Finally, we determine the location of the maximum correlation score over the search area to estimate the position of the USV. Comprehensive experiments are performed in a field trial in the archipelago. Our approach provides promising results by achieving position estimates with GPS-level accuracy.

2026-08-31T08:58:13Z 7 pages, 7 figures, 1 table. Published at IEEE IPAS 2018. An extended version appeared in Journal of Field Robotics 37(6):951-971, 2020, doi:10.1002/rob.21929 2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS), pp. 149-155 Bertil Grelsson Andreas Robinson Michael Felsberg Fahad Shahbaz Khan 10.1109/IPAS.2018.8708868 http://arxiv.org/abs/2608.29211v1 2026-08-29T11:52:21Z

Ground image localization with respect to satellite imagery is a key enabler for metrically-accurate, geo-localized 3D scene reconstruction from unconstrained image collections. Existing cross-view localization methods have strict requirements such as panoramic imagery or known initial locations, limiting their applicability for in-the-wild reconstruction settings. We propose a robust hierarchical cross-view localization framework that leverages geometric constraints from Structure-from-Motion (SfM) models derived from unconstrained ground image collections. Our method generates coarse-to-fine pose hypotheses through a cross-view matching approach and aggregates noisy predictions across SfM model(s) using Kernel Density Estimation to recover consensus alignments while filtering outliers. Experiments demonstrate reliable localization performance from challenging image collections. Empirically we found satellite-referenced alignment enables accurate metric scale estimation, doppelgänger detection, and merging of disjoint SfM reconstructions, resulting in more complete, geo-localized site models than are possible with SfM alone.

2026-08-29T11:52:21Z IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2026 Angel Daruna Ben Southall Niluthpol Chowdhury Mithun Kshitij Minhas Nicholas Meegan Qiao Wang Bogdan Matei Supun Samarasekera Rakesh Kumar http://arxiv.org/abs/2608.27073v2 2026-08-28T15:48:43Z

Explorable image-to-scene generation is essential for applications in gaming, robotics, and virtual reality. Existing methods based on video diffusion model (VDM) commonly rely on incomplete conditioning signals such as sparse point clouds or 2D panoramas, leading to stochastic hallucinations, long-term drifts and suboptimal 3D consistency. We present SpatialCrafter, a novel two-stage framework that addresses these issues by introducing a global 3D proxy for high-fidelity image-to-scene generation. Specifically, we decompose the generation process into global proxy generation and appearance refinement. For proxy generation, we propose a Point-anchored Sparse Structure~(PaSS) Flow module that predicts a spatially aligned and geometrically consistent 3D proxy. For appearance refinement, we re-frame the VDM as a Generative Deferred Refiner which synthesizes high-frequency photorealistic details upon proxy-defined scene geometry. To better integrate the proxy with the pre-trained VDM, we introduce Parallel Geometry Injection and Proxy-Aware Corruption training strategies, which improve robustness to proxy artifacts without disrupting the pretrained generative manifold. Furthermore, as no suitable dataset exists for this explorable scene generation task, we construct a new large-scale dataset of 115K scenes. To the best of our knowledge, it is the first hybrid dataset for image-to-scene generation. Extensive experiments on both synthetic and real-world datasets show that SpatialCrafter outperforms state-of-the-art methods, mitigates long-term drift, and remains robust and consistent under rapid camera motion and extreme viewpoint changes. Our project page: \href{https://fangchuan.github.io/SpatialCrafter/}{fangchuan.github.io/SpatialCrafter/}

2026-08-27T12:58:37Z 12 pages Chuan Fang Lingteng Qiu Yixun Liang Rui Chen Kunming Luo Zhaohua Zheng Tongyuan Bai Feipeng Tian Zilong Dong Zihan Zhou Ping Tan http://arxiv.org/abs/2608.23238v1 2026-08-24T13:25:34Z

We present Mover360, a controllable object manipulation framework for 360° images. Unlike perspective images, 360° images in equirectangular projection (ERP) exhibit horizontal wrap-around, latitude-dependent distortion, and global scene continuity, which makes object-level edits difficult for existing perspective editors to produce and for users to specify. To address this, Mover360 centers on object Translation (relocating a specified object within an existing panorama) while supporting reference-guided Insert and Remove as auxiliary tasks. Its interface unifies point-, bbox-, and mask-guided control by encoding each task into a fixed prompt and a compact, ERP-aligned instruction map. In the default point mode, a single click relocates an object, allowing the model to infer a plausible size, support, and illumination using panoramic context and an auxiliary depth condition. Structurally, Mover360 is a lightweight adaptation of a pretrained diffusion transformer. To generate paired supervision, we construct a UE5 data-generation pipeline with surface-aware object placement and randomized illumination, yielding large-scale paired data and a dual-domain benchmark of synthetic and real panoramas with ground truth for all three tasks. Across both test domains and two evaluation protocols, Mover360 outperforms strong baselines for perspective editing, insertion, and inpainting in reconstruction fidelity, semantic consistency, and distributional quality. Code and our benchmark dataset are available at https://zhonghaoyi.github.io/Mover360/.

2026-08-24T13:25:34Z Haoyi Zhong Fang-Lue Zhang Andrew Chalmers Taehyun Rhee http://arxiv.org/abs/2608.23140v1 2026-08-24T11:46:28Z

Achieving 360° coverage is critical for the visual perception systems of autonomous vehicles. Fisheye cameras offer a cost-effective solution by enabling full surround coverage with as few as two sensors. However, existing multi-view fisheye datasets are limited, and synthesizing rare corner cases typically requires computationally expensive 3D simulations, hindering the training. While generative models have achieved significant success in standard perspective imagery, their application to wide-angle distortion remains unexplored. In this work, we formally introduce the novel problem of multi-view fisheye image generation conditioned on volumetric semantic representations and present two distinct methods. We first propose SyntheOcc-FE, which adapts the SyntheOcc architecture to fisheye data. While effective, this method is constrained by the scarcity of fisheye datasets, which limits its generalization. To overcome these limitations, we propose our second method, MIVIFI (multi-view fisheye), which leverages cross-domain learning with Equirectangular Projections. By bridging the gap between dataset domains using KITTI-360 fisheye images alongside nuScenes multi-view standard images, our approach enables high-fidelity manipulation of scene content. This framework enables the structural modification of semantic occupancy inputs to introduce or eliminate specific actors and facilitates the rendering of diverse meteorological conditions and illumination scenarios absent in the limited fisheye datasets. Quantitative and qualitative experiments demonstrate that our methods achieve robust photorealistic multi-view fisheye image generation and highlight the specific advantages of our cross-domain strategy for handling data scarcity.

2026-08-24T11:46:28Z Accepted at the IEEE International Conference on Intelligent Transportation Systems (ITSC) 2026 Matthias Neuwirth-Trapp Begüm Altunbas Jiayi Wang Yan Xia Maarten Bieshaar Xinyu Huang Daniel Cremers http://arxiv.org/abs/2608.22039v1 2026-08-22T16:54:06Z

Structure-from-Motion (SfM) is a cornerstone of 3D perception, yet current methods often fail when applied to complex videos involving challenging camera motions or dynamic scenes. Compounding the problem, the field lacks reliable ground-truth benchmarks for such difficult scenarios, making it hard to gauge real-world progress or to pinpoint where improvements are most needed. To address this gap, we introduce a new benchmark for evaluating camera pose estimation. Our key insight is to leverage online panoramic 360° video as a source of data from which to construct challenging clips, while still enabling robust ground-truth trajectory recovery. The panoramic nature of these videos provides richer visual context for tracking camera motion, even when parts of the view are affected by blur, motion, or dynamic objects. After tracking camera motion across full 360° videos, we crop and reproject selected portions to generate perspective-view clips that serve as our benchmark, called ORBIT. Experiments show that COLMAP, as well as recent optimization-based and feed-forward SfM methods struggle to accurately estimate camera poses on our benchmark. Hence, ORBIT provides a valuable testbed where researchers can meaningfully measure progress on truly challenging, real-world SfM problems.

2026-08-22T16:54:06Z A revision was Accepted at CVPR 2026 Sara Sabour Linyi Jin Richard Tucker Amir Hertz Marcus Brubaker Saurabh Saxena Junhwa Hur Andrea Tagliasacchi Deqing Sun David J. Fleet Richard Szeliski Noah Snavely http://arxiv.org/abs/2608.20691v1 2026-08-21T02:59:34Z

Panoramic image generation is increasingly important for immersive applications such as virtual reality, augmented reality, and 3D content creation. Unlike perspective images, panoramic images represent a viewer-centered $360^\circ$ surrounding space, where directional expressions such as left, right, front, and behind play a central role in spatial understanding. However, existing text-to-panorama methods largely rely on implicit spatial reasoning and often fail to faithfully ground object-level directional descriptions in spherical panoramic scenes. A straightforward alternative is to introduce explicit layouts, but requiring manually specified spatial conditions reduces the flexibility of language-based interaction and does not directly resolve the misalignment between egocentric directional language and panoramic image space. To address this issue, we propose PanoCtrl, an object-centric framework for controllable text-to-panorama generation. Our method explicitly bridges natural language and spherical panoramic space by converting textual descriptions into structured object-level spherical conditions and integrating them into the diffusion process. Specifically, we introduce PanoParse, a text-conditioned parser that predicts object semantics and spherical bounding field-of-view (BFoV) parameters, and \textbf{PanoControl}, which injects object-level semantic and spatial guidance into the diffusion transformer through object-aware attention and spatial residual enhancement. To support this task, we construct PanoGround, a dataset with object-level spherical annotations and diverse directional descriptions for controllable panoramic generation. Extensive experiments demonstrate that PanoCtrl achieves state-of-the-art performance in both spatial alignment and image quality.

2026-08-21T02:59:34Z Derui Li Qian Qiao Yuhao Sun Wenhao Guo Peng Lu http://arxiv.org/abs/2608.19866v1 2026-08-20T10:21:57Z

This paper presents a novel data-driven approach to camera-based autonomy for micro-drones in GPS-denied, radio-challenging indoor environments. The target application is disaster and emergency response, where micro-UAVs can provide rapid situational awareness in hazardous settings such as firefighting and chemical, biological, radiological, and nuclear (CBRN) incidents while reducing risk for human responders. When the communication link is lost, the micro-drone uses a learned yaw controller to autonomously navigate toward open space, preserving onboard sensor data that would otherwise be lost with the vehicle. A custom micro-drone equipped with a 360-degree camera was used to record diverse industrial, underground, and training scenarios representative of communication-denied field operations. We introduce a preprocessing pipeline that converts equirectangular 360-degree footage into planar front views and dynamically generates image-label pairs for AI training. We then train and compare multiple convolutional neural network variants that predict a continuous yaw command from a single monocular view. Evaluation on a held-out test set confirms the feasibility of the learned yaw-prediction approach. A semi-autonomous real-world test further demonstrates the practicality of the method while revealing key failure modes, particularly reflections and glare.

2026-08-20T10:21:57Z Accepted at the 2026 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Genoa, Italy, July 6-10, 2026 Niklas Voigt Hartmut Surmann http://arxiv.org/abs/2608.15659v2 2026-08-19T05:36:59Z

Learning to generate or reconstruct explorable worlds requires video paired with more than RGB: camera motion, scene geometry, temporal correspondence and, for interactive models, control signals. Real capture can provide some of these signals, but dense geometry and long-range correspondence usually rely on estimation or specialised instrumentation. Rendering provides these quantities directly, yet existing synthetic resources rarely combine them on the same frames while also supporting controlled changes of viewpoint and appearance. We introduce WorldRover, a data engine for generating richly annotated, long-range explorations of artist-built environments. At its core, WorldRover-Engine is an Unreal Engine pipeline that executes and offline-renders minute-scale routes while preserving their full trajectories and scene geometry. The same exploration can be replayed from first-person, third-person, and 360 panoramic cameras under different environmental states. Using WorldRover-Engine, we construct WorldRover-10M, whose sequences pair RGB with metric depth, camera trajectories, and trajectory-derived action signals throughout each exploration. Third-person subsets additionally provide dense optical flow, long-range 2D/3D point tracks with visibility, and a character trajectory distinct from the camera trajectory. The engine can render a traversal from first-person, third-person and 360 panoramic viewpoints, under different environmental states or with a neutral white material, while preserving the route and scene geometry. WorldRover therefore turns long-horizon world exploration into a scalable data-generation problem, providing supervision for models that must build, maintain, and revisit coherent representations of an explorable world.

2026-08-16T10:06:59Z update code and data links Xiaojie Xu Zhengyuan Lin Runyi Li Yihao Liu Kaipeng Zhang Yongtao Ge http://arxiv.org/abs/2608.15284v1 2026-08-15T15:31:27Z

Navigation instruction generation from ego-centric RGB video in continuous environments is an important yet challenging task for human-robot interaction and scalable dataset construction. Prior instruction generators assume discrete viewpoint graphs with panoramic observations, where trajectory structure is explicit; in continuous environments, however, the agent receives only a dense RGB stream, making trajectory cues difficult to recover. We propose VTInstructor, the first VLN instruction generation framework for continuous environments. Our key idea is to convert implicit trajectory geometry into explicit visual trajectory prompts: EDTC condenses long RGB trajectories into navigation-critical keyframes, VTP overlays path, turn, and goal cues onto these anchors, VTMod injects the resulting trajectory signals into the visual encoder, and VT-GRPO further calibrates this spatial injection during training, all without requiring a navigation graph, pre-built map, or scene reconstruction. On the challenging R2R-CE and RxR-CE Val Unseen benchmarks, VTInstructor sets a new state of the art across all standard NLG metrics, surpassing the strongest baseline by +0.357 CIDEr and +0.109 CIDEr, respectively. Beyond automatic metrics, VTInstructor-generated instructions raise a frozen follower's success rate to 63.3%, a +14.7 percentage-point gain over the best competing instruction source, and provide consistent data augmentation gains of +3 SR points on downstream navigation tasks.

2026-08-15T15:31:27Z accepted by ACM MM 2026 Haolin Yang Yuxing Long Zihan Yang Hao Dong http://arxiv.org/abs/2608.11051v1 2026-08-11T15:22:14Z

As robots increasingly operate in human-populated environments, anticipating human intentions is essential for enabling proactive and socially aware behavior. Automatic anticipation of human-robot interactions is thus emerging as a crucial perception challenge for embodied agents. To this end, we introduce HUI360, the largest dataset for human-robot interaction anticipation in the wild and its set of baselines. The dataset was collected from a mobile robot, in the wild, over multiple days within a 3-month period, and in several environments, capturing natural, spontaneous behaviors from both passersby and users, and encompassing a diverse range of individuals. This variety enables evaluating and improving the generalization capabilities of interaction anticipation models. We designed a pipeline and share code for automatic interaction annotation in arbitrary 360-degree equirectangular videos, along with interfaces for manual refinement. Using this pipeline, we release the HUI360 open set of 1M pre-processed annotations, including detailed 2D poses, facial keypoints, and segmentation masks, obtained using state-of-the-art computer vision methods and manually curated to ensure high-quality tracking and interaction annotation. Additionally, we release the raw panoptic 360-degree images captured from the robot's egocentric viewpoint (on demand, for research purpose only in compliance with GDPR). Finally, we establish benchmark baselines for interaction anticipation, including the first cross-dataset evaluations for this task: to this end, we also release 6M annotations for another existing in-the-wild outdoor dataset collected from a mobile robot (SSUP-HRI). Dataset and code can be found at https://hucebot.github.io/hui360.

2026-08-11T15:22:14Z 2026 IEEE International Conference on Automatic Face and Gesture Recognition (FG) Raphael Lorenzo-Louis Fabio Amadio Bertrand Luvison Serena Ivaldi 10.1109/FG67764.2026.11556969 http://arxiv.org/abs/2608.09449v2 2026-08-11T09:05:36Z

Video world models must capture how scenes evolve over time and across viewpoints. Training them for long-horizon generation and camera control therefore benefits from long videos paired with camera trajectories and temporally grounded semantics. Existing corpora rarely offer the three together: large-scale web video provides broad visual diversity but no trajectories or time-aligned text, while pose-annotated datasets are typically short-range or reconstruction-oriented. We introduce Sekai2, a multi-source real-world video dataset that carries the world-exploration footage of Sekai toward interactive world modeling. The release contains 128,892 clips totaling 2,826 hours from 10,428 source videos across 113 countries or regions, and is deliberately weighted toward sustained observation: under a common 120-second decomposition, 43,594 segments reach the full two minutes and account for 51.4% of all footage. Every clip includes a released camera trajectory and hierarchical annotations disentangling subject motion, environment dynamics, static scene content, and camera behavior, resulting in 649,597 temporally grounded segments. Crucially, we further introduce 982 panoramic sequences captured along non-linear trajectories with loops and revisits. These revisits provide repeated observations of the same locations across time and viewpoints, offering essential supervision for learning persistent scene representations, long-term spatial memory, and geometrically consistent world models. Corpus-scale analyses demonstrate complete pose-and-caption coverage, broad geographic and semantic diversity, varied camera trajectories, and highly non-redundant temporal descriptions. Together, these properties make Sekai2 a scalable resource for long-horizon video generation, camera-controllable synthesis, and interactive world-model pre-training.

2026-08-10T11:23:01Z Sekai2 dataset technical report. Developed at Alaya Lab Kang He Wenshuo Peng Zihui Gao Jiaming Tan Kaipeng Zhang Yongtao Ge http://arxiv.org/abs/2608.06231v1 2026-08-06T16:20:23Z

Emotion shapes how viewers interpret a scene, yet existing video generators entangle global atmosphere, affect-bearing semantic cues, and temporal progression within a single text condition. We present EmoWorld, a framework that decouples these factors within a frozen flow-matching video diffusion transformer (Video DiT). A one-time preparation stage extracts layer-specific affect directions and a reusable cue library from geometry-preserving neutral and emotion-edited panoramas. At inference, Visual Atmosphere Steering (VAS) injects atmosphere directions into hidden states, Semantic Affective Steering (SAS) isolates a separately scalable prompt residual for semantic cues, and Temporal Affective Steering (TAS) interpolates endpoint residual fields across denoising and video time. On Wan2.2, VAS improves target-emotion alignment by 19% while reducing a temporal-fluctuation proxy by 48%; SAS improves target-emotion alignment by 37% and increases detected affect-bearing cues by 36%; and TAS improves transition monotonicity by 15% over the strongest baseline. EmoWorld is evaluated across 27 emotion categories in text-to-video and image-to-video settings, demonstrates portability across multiple Video-DiT backbones, and supports camera-conditioned composition without updating generator parameters.

2026-08-06T16:20:23Z Bingyuan Wang Baistan Zhyldyzbekov Kunyu Feng Zeyu Wang http://arxiv.org/abs/2608.05570v1 2026-08-06T03:42:50Z

360-degree video telepresence offers strong immersive potential but remains constrained by the limited resolution of current capture and display hardware. Many telepresence installations feature fixed viewpoints and largely static scenes, yet optimization strategies tailored to such setups have received limited attention. We present a multi-layer, ultra-high-resolution system for static 360-degree telepresence that combines an 8K panoramic camera with a rotatable 4K pan-tilt-zoom (PTZ) camera. Our approach builds a three-layer representation: (1) a tile-based ultra-high-resolution panoramic background, generated by offline stitching high-detail 4K PTZ scans onto the base 8K panorama to achieve effective resolution beyond native capture, and represented as a set of spatial tiles; (2) a dynamic update layer that composites foreground motions from the 8K stream via real-time high-resolution background matting; and (3) a region-of-interest 4K layer that streams a real-time PTZ view of the selected region and additionally updates the corresponding background tiles over time. We evaluate the proposed system through comparisons with representative video super-resolution approaches and a user study assessing perceived detail and immersive experience. Our results indicate that tile-based background refinement, together with user-guided updates, provides a practical way to balance panoramic fidelity and interactivity in static 360-degree telepresence.

2026-08-06T03:42:50Z 11 pages, 11 figures. Accepted to IEEE ISMAR 2026, to appear in IEEE Transactions on Visualization and Computer Graphics (TVCG) Jiapeng Chi Gerd Bruder Carsten Neumann Carolina Cruz-Neira Dirk Reiners http://arxiv.org/abs/2608.04720v4 2026-08-20T14:23:42Z

Real-time object detectors achieve remarkable accuracy under controlled conditions, yet degrade sharply on non-ideal inputs-fisheye distortion, game-rendered content, aerial views, and 360°panoramas. We present YOLOv14, a unified adaptive detection framework that addresses these variations through four complementary mechanisms, formalized under a novel Adaptive Routing and Modulation (ARM) paradigm. Unlike conventional unsupervised domain adaptation, our approach employs Target-Prior Guided Source-Domain Augmentation(TP-SDA), using only 50 unlabeled target images offline to estimate style statistics, while adversarial alignment serves as a lightweight regularizer rather than the primary adaptation driver. Together, these components enable YOLOv14 to achieve 49.1 mAP on COCO val2017 at 2.91 ms (T4 GPU), with substantial gains of +4.1 (fisheye), +6.6 (panorama), +6.4 (drone), and +26.1 (gamestylized) mAP over YOLOv12s. Crucially, we validate generalization on real-world game screenshots (GTA-V, Unity), achieving +14.2 mAP, confirming practical transferability beyond synthetic benchmarks. Code and models are released at https://github.com/zhangcbb/yolov14.

2026-08-05T11:39:06Z Sorry, we need to evaluate and revise the paper more scientifically Jian Lu Jinling Jia Jone Yawl Chenbin Zhang http://arxiv.org/abs/2608.02257v1 2026-08-03T14:03:26Z

Mobile manipulation is a key capability for embodied intelligence, enabling robots to accomplish complex multi-stage tasks in open-world environments. However, mobile manipulation poses two key challenges for vision-language-action (VLA) policies: At the data level, the efficient collection of high-quality whole-body demonstrations demands the coordinated control of both the mobile base and the robotic arms; at the model level, existing VLA models predominantly rely on local camera observations, whose limited field of view hinders global spatial understanding. To address these challenges, we develop a whole-body teleoperation system and a panoramic-aware VLA policy. The system enables coordinated control of a wheeled bimanual robot through a single VR interface and supports the acquisition of a real-world mobile manipulation dataset comprising 5.5 hours of multimodal demonstrations. Building upon this dataset, we propose PanoVLA, a panorama-aware vision-language-action policy for mobile bimanual manipulation. Built upon a Mixture-of-Transformers architecture, PanoVLA introduces global spatial context through dedicated panorama encoding and fusion modules, enabling effective integration of panoramic observations with language instructions and robot states for action generation. Evaluation on four real-world mobile manipulation tasks demonstrates that PanoVLA achieves an average stage completion rate of 91.3\% and an end-to-end success rate of 73.4\%, substantially outperforming local-view baselines. These results demonstrate that incorporating panoramic spatial context improves spatial understanding and closed-loop manipulation performance in mobile robots.

2026-08-03T14:03:26Z 8 pages, 4 figures Donglin Yang Haoran Chen Xingyu Chen Lixing Liu Manyi Li Changhe Tu Ke Xu Xiaojian Ma Si Liu http://arxiv.org/abs/2608.00463v1 2026-08-01T06:04:34Z

3D Gaussian Splatting (3DGS) turns captured or generated imagery into photorealistic 3D world simulations that users can freely explore, yet these worlds remain silent. Because existing audio generation methods condition on a single image or viewpoint, their sound is tied to that observation and cannot stay consistent while a listener moves. We introduce the task of generating a spatially consistent soundscape for a given 3DGS world through auditory grounding, identifying which objects in the world should emit sound and anchoring each to a persistent 3D position, and present Scene2Sound, a training-free framework built on this grounding. From the input world alone, our pipeline selects viewpoints that jointly cover the scene, identifies sound-emitting objects with a vision-language model, and associates the multi-view detections into 3D instances through Gaussian set matching, which measures the overlap between the Gaussian sets that render each detection. Each source then receives generated audio that a standard object-based audio engine spatializes in real time at arbitrary listener poses. We further propose two spatial-consistency metrics, one testing whether rendered audio responds consistently to listener motion and one testing whether the claimed sources are supported by views held out from their placement. On a curated set of generated 3DGS worlds and on 3DGS scenes generated from real-world 360-degree captures, Scene2Sound preserves the audio quality of strong per-viewpoint baselines while remaining spatially consistent where per-viewpoint and single-panorama pipelines do not, and a user study confirms the perceptual benefit. Project page: https://masaki-lmd.github.io/scene2sound/.

2026-08-01T06:04:34Z 14 pages. Project page: https://masaki-lmd.github.io/scene2sound/ Masaki Yoshida Ren Togo Takahiro Ogawa Miki Haseyama http://arxiv.org/abs/2607.27378v1 2026-07-29T18:36:07Z

Accurate evaluation of multimodal large language models (MLLMs) in dental panoramic radiography (orthopantomogram, OPG) is limited by the lack of fine-grained, clinically reliable benchmarks that reflect expert interpretation. This work introduces PanDent, a large-scale, clinically grounded OPG benchmark built upon fine-grained, expert-validated tooth-level annotations. The dataset comprises 9,524 high-quality OPGs, each associated with comprehensive structured annotations produced by experienced dentists and further validated by an oral and maxillofacial radiologist, providing clinically reliable supervision for tooth-level diagnosis and reasoning. Clinically consistent radiology reports are constructed from expert-validated findings using clinician-defined reporting logic, establishing explicit correspondence between structured clinical evidence and free-text descriptions. This design enables evaluation of whether MLLMs generate reports that are not only linguistically coherent but also clinically consistent with expert-validated tooth-level findings. Experiments are conducted on diverse MLLMs, including state-of-the-art (SOTA) proprietary models, general-domain open-source models, and medical-specific models. Results show that current MLLMs can generate fluent reports, yet fail to produce clinically consistent descriptions, exhibiting substantial errors in fine-grained localization and tooth-level diagnosis. Fine-tuning on PanDent significantly improves structure-language consistency, substantially enhancing visual localization accuracy and diagnostic correctness, and bringing model outputs closer to expert dental interpretation. These results establish PanDent as a rigorous benchmark for evaluating tooth-level clinical reasoning in MLLMs and a valuable resource for clinically grounded dental AI.

2026-07-29T18:36:07Z Xiaohan Li Xinyu Liu Chang Liu Sum Wing Au Yeung Jun Liu Yixuan Yuan Hui Chen http://arxiv.org/abs/2607.26646v1 2026-07-29T09:08:16Z

We address the problem of reconstructing a high-fidelity, freely navigable 3D scene from a single $360^\circ$ panorama, without per-scene optimization or multi-view capture. Existing methods either lack metric trajectory control, which hinders reliable downstream 3D reconstruction, or struggle with large disocclusions under long-range camera motion while requiring high-end multi-GPU servers.We present Genie Sim PanoWorld, a two-stage feed-forward pipeline that bridges generation and reconstruction via an explicit, trajectory-controllable panoramic video. A NavMesh-planned $\mathrm{SE}(3)$ roaming trajectory is injected into a latent video diffusion model through dense geometry-warped conditioning; long--short trajectory mixed training and a self-consistency objective based on shortcut models together yield high-fidelity video in four CFG-free denoising steps. A feed-forward panoramic reconstructor then lifts the generated video into a high-fidelity 3D Gaussian scene that supports real-time, free-viewpoint roaming and can be directly used as a simulation-ready asset for embodied AI applications. Experiments show that Genie Sim PanoWorld outperforms geometry-conditioned baselines in both panoramic video generation and downstream 3D reconstruction, while generalizing zero-shot to unseen indoor scenes.

2026-07-29T09:08:16Z Yongxin Su Linjie Hou Feng Wang Jialin Tang Zhijun Li Qian Wang Maoqing Yao http://arxiv.org/abs/2607.25362v1 2026-07-28T07:13:11Z

Reflections from shiny objects and glass facades naturally extend the field of view of a camera, capturing the surrounding environment without the need to pan the camera or acquire a full panorama. We propose PanoLess, a Gaussian-splat-based framework that reconstructs the surrounding environment as a distant illumination map from images captured on only one side of a reflective surface. PanoLess leverages surface-aligned 2D Gaussian splats with deferred shading to recover accurate per-pixel normals and reflection cues, which are fused into a neural cubemap representation of the environment. In addition, PanoLess produces a visibility map that explicitly denotes which regions of the environment are supported by the partial reflective observations. Unlike existing inverse-rendering and reflection-aware Gaussian-splatting approaches, which typically require full 360-degree coverage and struggle under incomplete views, PanoLess enables consistent, physically grounded illumination estimation from partial-view input. We show that PanoLess achieves high-fidelity and geometrically consistent environment reconstruction, outperforming reflection-aware baselines on a new custom synthetic benchmark and publicly available datasets, and demonstrating generalization to real-world reflective captures.

2026-07-28T07:13:11Z ECCV 2026. Main paper with supplementary material Ahitagni Das Ashok Veeraraghavan Vivek Boominathan http://arxiv.org/abs/2607.25215v1 2026-07-28T02:44:56Z

We want robots to localize in previously untraversed environments against commonly available prior data. Rich semantic data available from OpenStreetMap can be useful in this task. However, existing methods either ignore this semantic information, directly matching panoramas and overhead imagery, or dramatically compress the semantic information, working with a small set of fixed classes. To leverage this rich semantic information, two challenges need to be overcome. First, useful semantic information needs to be extracted from the robot's egocentric observations. Second, the observed information must be quickly associated with the large prior semantic map (e.g., up to 628 km^2). We show that VLMs are effective at both extracting relevant landmarks from panoramas, and identifying feasible correspondences between these landmarks and prior overhead landmarks. However, using VLMs to propose all correspondences scales poorly as the number of mapped landmarks increases. Instead, we propose distilling a lightweight matcher from a VLM which computes correspondences for all entities in a map. We use this output to form an observation likelihood which is fused over time with a Bayes filter to create a time series of pose estimates. To support further investigation into generalizable cross-view methods that leverage semantic information, we release a dataset of extracted semantics and evaluation trajectories spanning eleven environments, including panoramas we collected in a snowstorm and at night in Boston. We demonstrate our method, trained on a single city's fair-weather data, generalizes across location, lighting, weather, and other challenges. Code and datasets are available at https://efahnestock.github.io/loci/.

2026-07-28T02:44:56Z Equal contribution by Ethan Fahnestock and Erick Fuentes. 13 pages, 7 figures, and 5 tables Ethan Fahnestock Erick Fuentes Philip R Osteen Nicholas Roy http://arxiv.org/abs/2607.21953v1 2026-07-24T03:59:32Z

Unmanned aerial vehicle (UAV) communication is expected to support a wide range of low-altitude applications in 6G mobile networks. However, traditional statistical channel models provide limited accuracy in specific environments, while deterministic methods such as ray tracing usually rely on accurate three-dimensional environment models and involve high computational complexity. Existing multimodal channel prediction approaches mainly focus on large-scale metrics such as path loss, and remain insufficient for modeling small-scale parameters. To address these limitations, this paper proposes PanoLAMP, a Panoramic perception and vision-language model-based Low-Altitude Multipath Prediction framework. It adopts a pretrained vision-language model as the backbone and captures the propagation environment features through panoramic RGB-D observations collected at both the transmitter and receiver to predict the delay, power, azimuth angle, and zenith angle offset relative to the line-of-sight path. Experiments are conducted on a synthetic dataset containing 18,949 UAV-vehicle links across seven UAV altitudes. Experimental results show that the proposed method consistently outperforms representative baselines in both multipath parameters and statistical metrics, and demonstrates stronger generalization across different flight heights.

2026-07-24T03:59:32Z Zihang Zeng Shu Sun Meixia Tao Zhiyong Chen Jianhua Mo Xiangwen Gu http://arxiv.org/abs/2607.19676v1 2026-07-22T02:25:46Z

Civil aviation is safety critical and its operations, from flight decks and towers to ramps and maintenance, generate massive, heterogeneous data at the network edge. Yet cloud centric deployment of large Artificial Intelligence (AI) models often produces high task latency, lacks offline capability in communication denied environments, and requires centralizing sensitive data, raising privacy and sovereignty risks. Edge AI moves perception, prediction, and decision logic closer to the data producers via compression, collaborative inference, and split learning, thereby reducing latency, bandwidth, and exposure while enabling graceful operation during disconnections. This paper provides a panoramic view and a common understanding of edge intelligence tailored to civil aviation. We firstly articulate the operational motivations for edge AI, and then review recent techniques for edge inference and edge learning. We then introduce the organizational computing paradigms and the respective configurations in civil aviation environments; finally, we describe the emerging applications and the future research trends of edge intelligence in civil aviation. We argue that a refined edge solution can complement cloud foundations to deliver low latency, privacy preserving, and resilient AI services across the civil aviation lifecycle.

2026-07-22T02:25:46Z 8 pages, 2 figures, 2 tables 2025 5th International Conference on Information Communication and Software Engineering (ICICSE), Chongqing, China, 12 to 14 December 2025, IEEE, 2026 Wenbin Li Zhongtian Liao Bolin Liu Yongjie Zhou Jingling Wu Xiaoyong Lin Jing Chen 10.1109/ICICSE66971.2025.11429888 http://arxiv.org/abs/2607.11673v2 2026-07-14T04:32:07Z

We present ABot-3DWorld 0, a universal multimodal 3D world model that turns text, image, and video inputs into high-fidelity, explorable 3D worlds. At the heart of our framework is a unified Spatial Generative Primitive (SGP), a compact tuple of a high-quality panorama and a spatial point cloud that delivers an efficient description of any 3D space. Multimodal inputs are first lifted into this primitive; a 3D-consistent panoramic video generator then explores the primitive along a planned trajectory; finally, our panoramic video reconstruction engine converts the generated video into a clean, photorealistic 3D Gaussian Splatting (3DGS) world. This pipeline covers two regimes: rich inputs (multi-view sets, casual video) are lifted into the SGP through a geometry-rigorous recovery that mirrors the observed scene, while a single image or sentence is completed generatively into a creative world. The result is one low-barrier engine for general 3D content creation that further anchors generated worlds to geographic points of interest, enabling map-native spatial exploration at consumer scale. Experiments show that ABot-3DWorld 0 sets the state of the art among open-source methods and demonstrates stronger scene fidelity than Marble under rich multimodal inputs.

2026-07-13T15:14:48Z Official Page: https://abot-world.amap.com/plaza Mingchao Sun Luyang Tang Yu Liu Xu Yan Zhan Li Yunwei Zhang Fei Yu Zengye Ge Yumin Liu Jiacheng Zhang Yongchang Zhang Jiawei Zhang Zhicheng Liu Zhongxu Sun Tianjian Ouyang Wenzheng Chen Shixing Yang Nianfei Fan Guodong Sun Huan Li Zheng Zhou Yongze Li Yingliang Peng Mengmeng Du Yuan Liu Haozhe Shi Chunnuo Gong Chengzhen Yu Chunxue Jia Yang Liu Shiying Zeng Junnan Lai Hang Zhang Ning Guo Baoquan Chen Mu Xu Hongyu Pan http://arxiv.org/abs/2607.10050v1 2026-07-11T00:16:02Z

We present SyncSpace, a system that achieves both spatial alignment and visual consistency between a generated 3DGS world and physical space. We first scan the space via depth sensing to extract 3D bounding boxes, which we render into a layout-only panorama and feed as a geometric prior to a generative world model, producing a Gaussian splat scene in which objects are re-semantized to fit a target style without per-object control. We then align the generated scene to physical space with a coarse-to-fine registration algorithm, refined manually via pinch gestures when automatic registration does not converge. We demonstrate a hand-tracked engulfment interaction in which the virtual world rises to replace the physical space, and show a single space reskinned into multiple stylistically distinct worlds with its layout preserved.

2026-07-11T00:16:02Z 2 pages, 2 figures Qinchuan Zhang Weibo Xu Yunge Wen http://arxiv.org/abs/2607.09661v1 2026-07-10T17:59:32Z

In this work, we aim to address the challenge of long-range memory in panoramic world models by exploiting the rotation-equivariant property of omnidirectional representations, where rotation can be treated as an implicit geometric transformation.Building on this insight, we propose PanoWorld, which simplifies camera trajectories into translations via fixed headings for both current-action modeling and long-range memory through Dense Panoramic Ray-Conditioning (DPRC) and Geometry-aware Memory Augmentation (GMA).Then, a three-stage training pipeline is introduced to progressively optimize each component. To better evaluate physical consistency under large-scale spatial variations and diverse illumination conditions, where existing datasets are relatively stable, we construct World360, a large-scale dataset consisting of both real-world video clips collected via panoramic unmanned aerial vehicles and high-quality simulated clips generated by AirSim360.Extensive experiments on World360 demonstrate the effectiveness of PanoWorld, outperforming alternative methods by a large margin.Our models, training code, and dataset will be publicly available. More information can be found on our project page: https://lihaoy-ux.github.io/panoworld-page/.

2026-07-10T17:59:32Z Project page: https://lihaoy-ux.github.io/panoworld-page/ Code:https://github.com/Insta360-Research-Team/PanoWorld Haoyuan Li Dizhe Zhang Yuemei Zhou Xiangkai Zhang Haoran Feng Xiaofan Lin Wenjie Jiang Bo Du Ming-Hsuan Yang Lu Qi http://arxiv.org/abs/2607.09078v1 2026-07-10T03:49:45Z

Object detection is a fundamental component in numerous Unmanned Aerial Vehicle (UAV) applications, yet it has long been plagued by hindrances like occlusion or target pixel scarcity. Active Object Detection (AOD) provides a novel paradigm to address these challenges via active vision, while UAV-based AOD research remains scarce due to the lack of high-quality datasets and benchmarks for algorithm development and evaluation. To fill this gap, this paper presents ATRNet-LUDO, the first large-scale real-world dataset for UAV-Ground Active Object Detection (UGAOD). It contains 121,000 multi-view panoramic multi-target aerial images and 1.21 million local single-target slices, covering 10 vehicle targets across 40 scenarios. It enables the construction of diverse training and testing environments for UAV agent interaction and active observation policy learning. Based on this dataset, we establish a comprehensive evaluation benchmark for AOD policy learning methods. Most existing AOD policies rely on Deep Reinforcement Learning (DRL) but suffer from poor generalization. Evaluations on our benchmark reveal a significant generalization gap between training and testing performance, highlighting an urgent need for solutions. To this end, we leverage the Joint Embedding Predictive Architecture (JEPA) to construct a world model that enhances state representation learning, and propose AOD-JEPA by incorporating AOD-specific prior knowledge. Extensive experiments validate its effectiveness and superiority. We hope ATRNet-LUDO and the benchmark will advance research in the UGAOD field. The dataset and code are soon available at https://github.com/Leo000ooo/LUDO_dataset.

2026-07-10T03:49:45Z 18 pages, 19 figures, 5 tables Tianpeng Liu Xinhua Jiang Li Liu Qinmu Shen Siwei Tang Zhen Liu Yongxiang Liu http://arxiv.org/abs/2607.08765v2 2026-07-12T11:09:35Z

In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream task-specific fine-tuning. To address the lack of large-scale, high-quality training data tailored to in-context panoramic tasks, we propose Canvas360Dataset, a collection of 1M high-quality paired panoramic samples for style transfer, inpainting, outpainting, and editing, enabling effective supervision across diverse in-context generation scenarios. On the modeling side, Canvas360 enhances text-to-panorama generation through parallel depth generation, velocity circular padding, and similarity loss regularization, enabling the model to learn geometry-aware representations, capture object distortion details, and improve geometric consistency and global coherence. Furthermore, empowered by strong panoramic priors, Canvas360 enables a unified in-context panoramic generation framework that supports diverse downstream tasks via token-level concatenation, surpassing prior methods in both task coverage and modeling flexibility. Extensive experiments show that Canvas360 improves panoramic image fidelity, achieving particularly strong performance on the panorama-specific FAED metric and competitive or leading results across the reported quantitative evaluations. More information can be found on our project page: https://zry000.github.io/Canvas360/

2026-07-09T17:59:06Z Project page: https://zry000.github.io/Canvas360/ Github: https://github.com/Insta360-Research-Team/Canvas360 Haoran Feng Ruiyang Zhang Longyi Zhang Dizhe Zhang Lu Qi http://arxiv.org/abs/2607.05765v1 2026-07-07T02:42:41Z

Embodied navigation aims to build agents that interpret multimodal goals, reason in 3D space, and reach target destinations reliably in the real world. However, progress remains constrained by the lack of scalable, high-fidelity, and physically grounded interactive environments. Although real-world scanned datasets offer visual realism, they are limited by scale. In contrast, synthetic simulators scale more easily but often exhibit large sim-to-real gaps. We introduce Image2Sim, a real-time neural simulation framework that constructs high-quality interactive environments from posed RGB-D image sequences. The central idea is to decouple 3D spatial anchoring from photorealistic observation synthesis. For scene construction, Image2Sim uses a feed-forward feature Gaussian model that lifts posed RGB-D observations into a 3D feature-Gaussian representation in a single pass. For rendering, we propose a Geometry-Aware One-Step Pixel Flow model that transforms sparse and noisy Gaussian projections into high-quality panoramic RGB-D observations. Image2Sim also serves as a fully automated embodied data engine that generates high-fidelity observations, executable actions, and diverse navigation instructions at scale. It converts large collections of videos and images into nearly 20K interactive scenes and synthesizes more than 10 million navigation training samples. Navigation models trained entirely in these neural environments achieve strong improvements on major benchmarks and transfer effectively to real-world zero-shot settings. These results suggest that scalable neural simulation can serve as a practical training substrate for embodied navigation at scale.

2026-07-07T02:42:41Z Zihan Wang Seungjun Lee Yinghao Xu Gim Hee Lee http://arxiv.org/abs/2607.03990v1 2026-07-04T19:16:29Z

Recent advances in single image-to-3D generation have enabled high-quality asset synthesis, yet extending these capabilities to indoor scene generation remains challenging. Existing methods focus on asset-level generation while neglecting the structural layout, which is essential for downstream applications and serves as the spatial anchor for grounding assets. However, a single image with a limited field of view lacks the spatial coverage to recover a coherent global layout. To this end, we use a 360° image represented in equirectangular projection (ERP) and propose InSpace, a structure-aware framework for 3D indoor scene generation. InSpace comprises three stages: (1) estimating partial scene geometry as spatial priors, (2) generating coarse scene structure with view-selective cross-attention, and (3) producing detailed layout and asset geometry with textures through a global-local hybrid attention, using flow matching. We also propose ERP-FRONT, a paired ERP-Image-to-3D indoor scene dataset based on 3D-FRONT. Experiments show that InSpace generates complete 3D indoor scenes with structural layout, along with separate textured assets from a single ERP image, achieving strong performance across 3D and 2D metrics. Project Page: https://kookie12.github.io/InSpace-Project-Page/

2026-07-04T19:16:29Z ECCV 2026 Gwanhyeong Koo Hyunsu Kim Youngji Kim Taejae Lee Siwoo Lim Sunjae Yoon Suyong Yeon Chang D. Yoo http://arxiv.org/abs/2607.02099v1 2026-07-02T12:34:59Z

Generating a 3D dental volume from a single panoramic radiograph (PXR) could provide a low-radiation alternative to Cone-Beam Computed Tomography (CBCT), but the problem is highly underdetermined: panoramic acquisition integrates 3D attenuation along curved X-ray paths into a 2D image, leaving depth-resolved anatomy unobserved. Existing implicit and generative approaches often produce oversmoothed geometry or anatomically inconsistent hallucinations, lacking geometry-driven supervision and relying on smooth representations unable to precisely localize sharp anatomical boundaries. We propose X-Splat, the first Gaussian Splatting framework for generating CBCT-like 3D dental volumes from a single PXR. X-Splat uses the known panoramic acquisition geometry as a generation scaffold: learnable anisotropic Gaussian primitives are initialized along the X-ray paths that formed the input image and adjusted in a single feed-forward pass, constrained by Beer-Lambert reprojection and multi-view radiographic training supervision. A lightweight residual refiner adds dataset-level anatomical priors without overriding the geometry already resolved by the Gaussians. We train on synthetic PXR-CBCT pairs, enabling direct volumetric supervision without paired real scans. We further introduce segmentation-based geometry-aware metrics, providing the first evaluation of PXR-based generation over maxillofacial anatomy. X-Splat outperforms NeRF- and GAN-based baselines, recovering individual teeth, cortical boundaries, and alveolar structure, including the mandibular canal which prior methods fail to reconstruct. Code will be available at https://github.com/tomek1911/X-Splat

2026-07-02T12:34:59Z 19 pages, 6 figures, including appendix. Under review Tomasz Szczepański Szymon Płotka Michal K. Grzeszczyk Tomasz Trzciński Arkadiusz Sitek http://arxiv.org/abs/2607.01663v1 2026-07-02T03:43:06Z

4D scene synthesis from monocular videos has made significant progress in recent years. However, existing methods are typically constrained by view interpolation. As a result, they struggle to infer unseen regions beyond the observed views. In this paper, we reformulate the task as 4D scene synthesis with unseen regions, which extends beyond traditional interpolation settings. Camera-conditioned video generation enables unseen region synthesis by guiding generation along specified cameras. However, these methods lack explicit 3D priors and are optimized with random camera trajectories. This design leads to severe inconsistencies under large trajectory deviations. To address this limitation, we build a unified training and inference framework with panoramic trajectory guidance. While this design improves cross-view consistency, the panoramic representation alone fails to model dynamic content effectively. Object motion in panoramic space introduces scale and shape distortions. To address this, we propose PanoGaussian, a unified Panoramic-Gaussian representation that distills the panoramic representation into an explicit dynamic Gaussian representation to capture dynamic physical priors of the 4D scene. Experiments demonstrate that PanoGaussian achieves consistent 4D scene synthesis even under large viewpoint variations.

2026-07-02T03:43:06Z Accepted at ECCV 2026 Yuankun Yang Yi Wei Wenyang Zhou Li Zhang http://arxiv.org/abs/2607.00832v2 2026-07-06T11:37:36Z

A single panorama captures the full visual sphere from one camera center, yet confines users to looking around in place without enabling true scene exploration. Converting a single panorama into a persistent, renderable 3D representation for free-viewpoint navigation has attracted growing interest; existing methods either adopt iterative per-view completion that propagates inpainting results to update the underlying geometry, leading to progressive error accumulation and cumbersome multi-step pipelines, or leverage the temporal consistency priors of video generation models, yet the continuous-trajectory constraint intrinsic to such models limits their flexibility in covering scenes from multiple directions simultaneously. We present Pano2World, which takes a single indoor panorama as input and directly outputs a persistent, explorable 3D Gaussian scene. Given the source panorama, Pano2World first reconstructs a coarse 3D Gaussian proxy and renders it at adaptively sampled nearby poses to obtain geometrically aligned guidance panoramas; a panoramic diffusion model then jointly denoises all target views via View-Aware Attention Routing, where each target view simultaneously receives geometric constraints from its corresponding guidance panorama and global semantic guidance from the source panorama, naturally enforcing cross-view consistency. To avoid the information loss incurred by decoding the multi-view hidden features formed during joint denoising back to the pixel domain via VAE, we introduce Latent Feature Adapter, a geometry-aware bridge module that directly distills these hidden features into a scene latent, subsequently decoded into the final 3D Gaussian scene. Experiments demonstrate that Pano2World significantly outperforms existing methods on the multi-position panoramic novel-view synthesis benchmark.

2026-07-01T11:54:02Z 10 pages, 3 figures, 3 tables. Preprint Zhenjia Li Jinrang Jia Yifeng Shi http://arxiv.org/abs/2606.32033v1 2026-06-30T17:57:04Z

We present a zero-shot, training-free and optimization-free framework for generating 360 panoramic images and videos by directly injecting spherical priors into pre-trained diffusion transformers. Existing methods either rely on costly fine-tuning on scarce panoramic data that limits generalization, or leverage multi-step optimization that incurs prohibitive inference latency. We observe that contemporary generative models natively exhibit some panoramic priors from large-scale training. However, these emergent capabilities are insufficient, as the models fundamentally fail to satisfy the rigorous topological constraints imposed by equirectangular projection (ERP). We introduce a zero-shot and optimization-free approach that resolves these constraints at inference time. Spherical RoPE replaces standard rotary position embeddings: low-frequency channels are re-parameterized as 3D Cartesian coordinates to natively encode the spherical manifold, while high-frequency channels are harmonically quantized to enforce exact periodicity. Coupled with complementary Semantic Distortion classifier-free guidance (CFG) that explicitly steers geometry, we avoid retraining and inherit the full creative breadth of state-of-the-art models. Our approach generalizes across diverse backbones and 360 generation modalities. We demonstrate this across text-to-panorama using Flux.1, Flux.2, and LTX-Video backbones, achieving competitive performance against baselines, all while remaining training-free. Project page: https://orhir.github.io/SpheRoPE

2026-06-30T17:57:04Z Or Hirschorn Aaron Olender Eli Alshan Ianir Ideses Lior Fritz Sagie Benaim http://arxiv.org/abs/2606.30352v1 2026-06-29T14:23:12Z

Recent advances in 3D scene reconstruction have highlighted the intricate trade-offs among rendering quality, inference efficiency, and data dependency. To address the challenge of rapidly reconstructing detailed 3D indoor scenes from minimal input, we introduce FastPano3D, an end-to-end framework that directly generates renderable 3D Gaussian representations from a single panoramic image. Unlike perspective-based methods, panoramic images inherently suffer from equirectangular projection distortions and spatially non-uniform feature distributions, making direct feed-forward Gaussian generation particularly challenging. In contrast to existing Gaussian Splatting based methods that rely on multi-view supervision or per-scene optimization, FastPano3D employs a lightweight feature encoder, adaptive Gaussian sampling, and a point-cloud-guided refinement strategy to achieve efficient and accurate scene generation without any test-time optimization. Our approach reconstructs high-fidelity 3D scenes within seconds, achieving up to 156 times faster inference than prior state-of-the-art methods such as Pano2Room, while using only half the parameters. Extensive experiments demonstrate that FastPano3D delivers rendering quality comparable to NeRF- and 3DGS-based reconstructions, establishing a new benchmark for rapid, single-view 3D scene inference.

2026-06-29T14:23:12Z Preprint. Under review. 20 pages, 9 figures Jianqiang Li Liumei Zhang Wenjia Guo Tianlong Feng Yongzhi Liao Di Lu Hanchi Ren Jingjing Deng 10.2139/ssrn.6986028 http://arxiv.org/abs/2606.29910v1 2026-06-29T07:46:08Z

Multi-camera visual-inertial odometry (VIO) overcomes the inherent limitations of pure visual systems by expanding the field of view. However, existing algorithms are typically tailored for fixed camera setups and lack unified compatibility with heterogeneous multi-camera systems. Meanwhile, due to the absence of a unified cross-camera representation and association mechanism, current methods struggle to achieve a balance among robust cross-camera feature tracking, stable depth estimation, and reliable real-time performance. To address these issues, we present Sphere-VIO, a lightweight filter-based VIO framework with unified spherical representation for heterogeneous multi-camera systems. Specifically, we first propose a Unified Spherical Panorama Model (USPM) that supports all standard camera models and enables bidirectional fast mapping between multi-camera images and a shared spherical space without sequential stitching, simplifying cross-camera feature management and improving triangulation efficiency. Second, we design a parallel-accelerated depth-guided semi-direct tracking pipeline, namely Hierarchical Omnidirectional Feature Alignment (HOFA), with global spherical constraints for robust cross-camera matching, and fuse multi-camera depth observations into a standard depth filter for stable initialization. Finally, we develop a multi-camera-adapted ESKF backend that employs spherical bearing residuals and Schur complement marginalization to minimize computational overhead, enabling accurate real-time state estimation on resource-constrained devices. Extensive experiments on public benchmarks and a custom omnidirectional dataset show that Sphere-VIO achieves superior trade-offs between accuracy, robustness, efficiency, and cross-camera generality.

2026-06-29T07:46:08Z Yueteng Yang Yusen Xie Hao Wei Qianhao Wang Boyu Zhou Fei Gao Jun Ma Jinni Zhou http://arxiv.org/abs/2606.29794v1 2026-06-29T05:14:48Z

Existing 3D Gaussian Splatting (3DGS) frameworks rely on camera-specific rasterization, suffering from inconsistent solid-angle sampling and degraded performance across heterogeneous camera models (e.g., perspective, fisheye, omnidirectional). To address this limitation, we propose UniTriSplat, a unified 3DGS framework for universal cameras that reformulates Gaussian splatting on the unit sphere via HEALPix discretization. Leveraging the equal-area property of HEALPix, we construct a spherical sampling grid aligned with the angular resolution of input images. We derive the forward rendering and gradient propagation of Gaussians directly in the spherical radian domain, yielding uniform optimization behavior from narrow-FoV images to full 360-degree panoramas. To enhance perceptual reconstruction quality, we additionally introduce a HEALPix-aware SSIM loss that respects spherical neighborhood structure. Extensive experiments across diverse camera models demonstrate that UniTriSplat consistently improves cross-camera generalization while preserving geometric fidelity and rendering quality.

2026-06-29T05:14:48Z 32 pages, 14 figures, 6 tables. Project page: https://yipengzhu0809.github.io/UniTriSplat/ . UniTriSplat was accepted to ECCV 2026 Yipeng Zhu Huajian Huang Tristan Braud Sai-Kit Yeung http://arxiv.org/abs/2606.27745v2 2026-07-15T13:11:28Z

Panoramic images capture the full visual sphere in a frame, offering context unavailable to conventional cameras. Yet this completeness has an unavoidable geometric cost: the 2-sphere cannot be faithfully mapped to the plane, and every projection introduces distortions that challenge standard vision architectures. This survey traces panoramic scene understanding from projection-based adaptation and distortion-aware engineering to sphere-native modeling, reflecting increasing commitment to spherical geometry. Foundation models form a fourth family, geometry-aware tokenization, which adapts the input interface while reusing perspective-pretrained weights. We review these approaches across five task families: dense prediction, unified multi-task understanding, open-world perception, vision-language reasoning, and dynamic video analysis. Across tasks, the same shift toward spherical geometry recurs. In practice, however, the field has converged not on the strongest sphere-native operators, which are exactly rotation-equivariant but cannot reuse perspective-pretrained backbones and thus have not scaled, but on a compatibility-preserving middle ground combining moderate geometric awareness with large pretrained models. This commitment is uneven: deepest in dense prediction and shallowest in dynamic perception, where methods are spatially sphere-aware yet temporally planar. Foundation-model adaptation has advanced panoramic depth fastest, while layout, surface-normal, and video-level understanding remain largely unexplored. No panoramic foundation model has yet been pretrained on spherical data. We identify five evaluation gaps: spherical-area-weighted metrics, seam-consistency tests, polar-robustness stratification, cross-projection generalization, and standardized open-world protocols. We conclude with a six-point roadmap toward general-purpose panoramic intelligence.

2026-06-26T05:54:38Z Qinfeng Zhu Lei Fan http://arxiv.org/abs/2606.27071v2 2026-07-09T14:24:02Z

Panoramic sensing offers wide field-of-view coverage, yet 3D reconstruction from sparse panoramas remains challenging under rotation-dominant, weak-parallax motion. In such regimes, SfM/SLAM initialization is often ill-conditioned and unreliable. We present PanoImager, an SfM-free framework that combines feed-forward pose/depth priors, geometry-conditioned diffusion view completion, and depth-guided 3DGS optimization. Given only a few panoramic images, PanoImager decomposes them into local perspective views, synthesizes auxiliary observations to enrich sparse evidence, and stabilizes Gaussian optimization for improved cross-view consistency. Experiments on multiple benchmarks show improved stability under extreme sparsity, suggesting PanoImager as an offline/background component for map refinement when SfM/SLAM fails to initialize.

2026-06-25T14:15:09Z IROS 2026 Zhisong Xu Takeshi Oishi http://arxiv.org/abs/2606.24476v3 2026-08-16T09:01:50Z

As sixth-generation wireless systems evolve from reliable connectivity toward environment intelligence, wireless world models aim to learn how physical environments and user states affect wireless propagation, requiring real-world data with explicit correspondences between channel responses and environment observations. However, existing channel-environment datasets are predominantly simulation-based or designed for specific communication tasks, limiting their support for general environment-channel relationship learning. To address this gap, we construct WiWorld-RealData, a real-world multi-band channel and multi-modal environment sensing dataset for 6G wireless world model research. It provides synchronized channel impulse responses measured at 3.7 and 6.775 GHz together with multi-view and panoramic images, light detection and ranging point clouds, millimeter-wave radar observations, and global navigation satellite system trajectories. Unified timestamps, sample identifiers, and metadata establish sample-level correspondences across these heterogeneous modalities. The overall measurement campaign produced approximately 10 TB of data, while the current public release provides aligned channel-environment samples from a representative continuous outdoor route. A path-loss prediction case study further validates the dataset using a continuous test route segment, achieving a mean absolute error of 2.02 dB and a root mean square error of 2.69 dB under few-shot adaptation. WiWorld-RealData supports cross-band propagation analysis, environment-aware channel modeling, wireless digital twins, and channel foundation model research. The dataset is available at https://scc.bupt.edu.cn/dataset-manage/datasets/44 and https://doi.org/10.57760/sciencedb.40663.

2026-06-23T12:09:58Z 6 pages, 6 figures, 3 tables Yinyin Jiao Huixin Xu Jianhua Zhang Yuelong Qiu Jingjing Wang Shaoyi Liu Yuxiang Zhang Li Yu Xuebin Sun Guangyi Liu http://arxiv.org/abs/2606.24234v2 2026-07-07T08:54:08Z

Autonomous robotic inspection in maritime environments presents unique challenges for Visual Place Recognition (VPR) due to cross-scene perceptual shifts. Robots navigating ship-borne environments must transition between visually distinct domains: open decks with sparse textures and severe illumination changes, and enclosed cabins with repetitive structures and high visual ambiguity. Existing VPR methods, designed primarily for urban or indoor scenes, fail to generalize reliably across these starkly different scenarios. To address this, we propose ProteusVPR, a two-stage retrieval-refinement framework. The first stage employs any standard VPR model for initial image retrieval. The second stage introduces a geometric-visual estimation network that fuses the retrieved image with two temporally preceding frames, incorporating geometric descriptors, a local affine coordinate system, and camera azimuth encoding to achieve precise localization. To support this task, we introduce the XHZ dataset, an 8K-panoramic ship-borne dataset collected from an operational vessel, featuring multi-floor cabin structures, deck transition zones, and strict query-database separation for rigorous evaluation. Extensive experiments on the XHZ dataset demonstrate that ProteusVPR consistently improves the localization accuracy across multiple VPR backbones, reducing mean localization error by over 60\% on average and that ProteusVPR offers an effective and robust solution for precise visual localization in challenging, cross-scene maritime environments.

2026-06-23T07:22:54Z Zexi Chen Zitai Huang Qiwen Gu Zhiqi Li Shengli Dong Chenlei Wang Junqiao Zhao Hongdong Wang Bing Han http://arxiv.org/abs/2606.22971v1 2026-06-22T07:52:25Z

Occupancy prediction at voxel-level granularity is essential for safe robotic navigation and interaction in complex environments. Existing occupancy datasets, however, are predominantly designed for autonomous driving with vehicle-centric biases -- forward-facing cameras, far-field geometry, and static road priors -- limiting their applicability to embodied humanoid perception. We present Humanoid-OmniOcc, a large-scale panoramic stereo-based occupancy dataset tailored for humanoid robots. The dataset encompasses 15 diverse simulated indoor scenes and 5 real-world environments, yielding over 155K samples with broad scene and style diversity. Importantly, the dataset is designed around a Real2Sim2Real closed-loop paradigm: real sensor specifications drive physically accurate simulation, simulation produces large-scale annotated training data, and models trained in simulation are directly evaluated on real-world captures -- enabling iterative refinement of the sim-to-real pipeline. We further propose \textbf{H}umanoid \textbf{S}urround \textbf{S}tereo-guided \textbf{Occ}upancy model (Humanoid-OmniOcc) that exploits robust depth priors for accurate 2D-to-3D lifting. Extensive experiments show that Humanoid-OmniOcc consistently outperforms monocular baselines and generalizes well to both unseen simulated test scenes and real-world environments, validating the effectiveness of the Real2Sim2Real design. Code and data will be available upon acceptance at https://d-robotics-ai-lab.github.io/humanoid-omniocc.

2026-06-22T07:52:25Z Xianda Guo Bohao Zhang Chenwei Huang Shiyuan Chen Ruilin Wang Yiqun Duan Cong Yang Qin Zou Wei Sui http://arxiv.org/abs/2606.19253v1 2026-06-17T16:29:19Z

Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets in pursuit of spatial reasoning. Instead, OneCanvas aggregates patch features from all views onto a single equirectangular panoramic canvas. Namely, each patch is unprojected to a 3D world coordinate using its depth and camera pose, then placed on the canvas at the continuous longitude and latitude of that point as seen from the canvas origin, with no rasterization or aggregation across overlapping views. A 3D position embedding of the patch's metric coordinates is added to its feature, restoring the depth lost when collapsing the world position to an angular canvas coordinate. Patches from all frames thus share one spatial coordinate system with no fusion or major architectural modifications of the backbone. The pretrained VLM consumes this representation as if it were an ordinary image. Because the canvas can be centered on any pose of interest, the same representation directly supports situated reasoning from a specific viewpoint, a common requirement in robotics and embodied AI. Thanks to this representation, we can also introduce a spatial pretraining curriculum: by procedurally placing patch features of objects, drawn from real images, at chosen 3D world positions on an otherwise empty canvas, we generate on-the-fly supervision spanning a broad range of spatial reasoning tasks, with answer distributions controlled to reduce spatial reasoning shortcuts. OneCanvas achieves state-of-the-art accuracy on SQA3D and VSI-Bench, and generalizes to out-of-distribution data on SPBench, using an order of magnitude less training compute than the strongest competing methods.

2026-06-17T16:29:19Z Project page: https://baranowskibrt.github.io/onecanvas/ Bartłomiej Baranowski Dave Zhenyu Chen Matthias Nießner http://arxiv.org/abs/2606.17520v1 2026-06-16T05:00:42Z

Training embodied agents in the real world requires skilled operators and expensive hardware. Simulation environments offer a compelling alternative by enabling large-scale, cost-effective data augmentation. Consequently, rapidly constructing high-fidelity simulation scenes with a minimal sim-to-real gap has become a critical objective in robot learning. While reconstruction-based methods provide superior visual quality, current workflows are hindered by inefficient data acquisition and subpar foreground object extraction. We thus propose GASE, a highly automated system for simulation scene construction. GASE leverages multi-view video streams from panoramic camera arrays to enable rapid environment scanning. To ensure high-quality asset generation, our pipeline introduces a camera-pose-based strategy that robustly extracts objects across frames in the 2D domain, followed by high-fidelity scene inpainting. Foreground objects and the static background are then reconstructed independently and seamlessly imported into physics simulators for policy training. Extensive experiments demonstrate that GASE outperforms existing 3D Gaussian-based methods in segmentation accuracy by over 10\% while achieving state-of-the-art inpainting quality. Furthermore, real-robot deployments across manipulation and navigation tasks maintains a performance gap of less than 10\% compared to policies trained purely on real-world data. These results confirm that GASE provides an efficient and highly effective solution for bridging the sim-to-real gap. Code will be released.

2026-06-16T05:00:42Z Jiawei Zhang Yiming Yan Chao Liang Nuo Xu Seson Sun Qichen Zhang Yuhao Xu Yantai Yang Yingqiao Wang Qin Jin Zhipeng Zhang http://arxiv.org/abs/2606.14035v1 2026-06-12T02:18:52Z

Zero-shot text-guided diffusion has significantly advanced image editing; however, its practical usability remains constrained by three persistent challenges: prompt brittleness that requires meticulous prompt engineering, spillover edits that unintentionally affect non-target regions, and failures on small or cluttered objects caused by limited fine-grained supervision in training data. We propose FocusDiff (Target-Aware Refocusing for Tuning-Free Diffusion Editing), a tuning-free framework for precise and region-specific image manipulation based on refocusing cross-attention. Given a target region obtained through automated segmentation or manual selection, FocusDiff applies selective blurring to non-edit areas to guide attention toward the masked region while accurately transferring the object's identity, structure, and appearance to the edited output. Integrated context-preserving modules further ensure background fidelity and global coherence, enabling accurate edits from simple text prompts in a single pass. We also extend FocusDiff to 360-degree indoor panorama editing and demonstrate its effectiveness within virtual reality environments. Extensive experiments on our localized editing benchmark LIMB, comprising 30 multi-object images and 100 annotated examples including challenging small-object cases, show that FocusDiff outperforms existing zero-shot editors in text-image alignment and background preservation, achieving superior precision, photorealism, and usability. The project page is available at https://vdkhoi20.github.io/FocusDiff.

2026-06-12T02:18:52Z ICCCI 2026. Project page: https://vdkhoi20.github.io/FocusDiff Dinh-Khoi Vo Nhut-Thanh Le-Hinh Viet-Tham Huynh Tam V. Nguyen Minh-Triet Tran Trung-Nghia Le http://arxiv.org/abs/2606.13376v2 2026-06-17T16:38:12Z

We present MoVerse, a real-time video world model that creates an interactively navigable scene from a single narrow-field-of-view image. This setting is challenging because the input observes only a small fraction of the environment, while interactive roaming requires a complete surrounding world, persistent geometry, controllable camera motion, and temporally coherent high-fidelity observations. MoVerse addresses this problem by separating world construction from observation rendering. It first expands the input into a gravity-aligned 360$^\circ$ panorama with topology-aware diffusion, closing the missing field of view before 3D reasoning. It then lifts the panorama into a persistent 3D Gaussian scaffold using panoramic geometry-aware residual prediction, yielding a dense and directly renderable spatial memory. Finally, a Gaussian-conditioned video renderer translates scaffold renderings along user-specified camera trajectories into photorealistic video. To make this renderer practical for interaction, we train a bidirectional diffusion teacher for high-quality conditional rendering and distill it into a causal autoregressive student for bounded-latency streaming. This design combines the controllability and long-range consistency of explicit 3D representations with the perceptual quality of generative video models. MoVerse supports real-time scene roaming at 8~FPS on a single NVIDIA RTX~4090 GPU, demonstrating a practical path toward single-image world creation with interactive video output.

2026-06-11T14:01:02Z Project Page: https://orange-3dv-team.github.io/MoVerse/ Yang Zhou Ziheng Wang Yuqin Lu Haofeng Liu Jun Liang Shengfeng He Jing Li http://arxiv.org/abs/2606.12368v2 2026-06-11T05:24:02Z

While monocular depth estimation has achieved significant progress, achieving generalized metric depth estimation for both narrow field-of-view (FoV) perspectives and $360^\circ$ panoramas remains an unsolved challenge. Existing methods are often tailored to specific camera types and struggle to produce accurate metric depth that generalizes across diverse settings. This limitation stems from two key challenges: the inherent geometric discrepancy between perspective and panoramic cameras, and the scarcity of panoramic training data with metric annotations. In this work, we introduce DepthMaster, a unified metric depth estimation framework. Rather than employing specialized networks to learn spherical distortions, we reformulate the problem by decomposing panoramic images into overlapping perspective patches. Crucially, distinct from prior projection-based methods that rely on ad-hoc architectural modifications to handle boundaries, we introduce a novel Correspondence Consistency Loss (CCL) and inject virtual projection cameras as geometric priors, allowing us to seamlessly stitch the patches while avoiding specialized operators and keeping the backbone largely compatible with standard Transformer designs. This strategy also resolves the geometric differences by unifying all inputs into a canonical perspective representation, and effectively circumvents data scarcity by directly unlocking powerful metric priors from vast perspective datasets. Trained on a mixed dataset that contains only one panorama dataset, DepthMaster achieves state-of-the-art zero-shot performance on 13 diverse datasets, outperforming not only universal methods but also leading specialist models in both perspective and panoramic domains.

2026-06-10T17:35:23Z Pengfei Wang Shihao Wang Liyi Chen Zhiyuan Ma Guowen Zhang Lei Zhang http://arxiv.org/abs/2606.12213v1 2026-06-10T15:29:06Z

Panoramic imagery is increasingly used in world-generation, games, and simulation, where users may need not only photorealistic scenes but also stylized and non-photorealistic environments. Large-scale text-to-image diffusion and flow models provide broad style and semantic priors for this goal, but planar image training misaligns them with the wrap-around topology and polar regions of $360^\circ$ panoramas represented in equirectangular projection (ERP). We present SHERPA, a lightweight adaptation framework that combines frequency-selective Circular RoPE, Circular Latent Encoding/Decoding, image-side FFN adapters, and a Dual-Path Training Scheme. Circular RoPE replaces only the seam-sensitive high-frequency horizontal RoPE band with integer-periodic harmonics while preserving the pretrained lower-frequency spectrum. The Paired Panorama Path supervises geometry, while the Unpaired Style Path uses self-supervised yaw consistency for target-free stylized prompts. As a result, SHERPA generates $360^\circ$ panoramas across both photorealistic panorama domains and open-domain stylized prompts.

2026-06-10T15:29:06Z 29 pages, 23 figures, 5 tables. Preprint version Jungwoon Kang Jaehun Kim Yiwon Yu Hyungyum Jang Sanghoon Lee Jongyoo Kim http://arxiv.org/abs/2606.09507v1 2026-06-08T13:59:50Z

Video world models have made rapid progress in generating controllable visual experiences, but most of them still simulate the world from a single observer. Extending such models to multiple agents raises a central challenge: if each agent's future state is generated independently, overlapping views may instantiate different versions of the same scene, leading to inconsistent objects, layouts, and appearances across agents. Conventional camera conditioning controls individual trajectories, but it does not explicitly couple the generation of views that should agree under shared scene geometry. We introduce Prisma-World, a camera-controllable multi-agent world model that formulates multi-agent generation as a joint geometry-aware denoising process for cross-view consistency. Prisma-World processes all agent videos within one full-attention sequence, uses a multi-agent RoPE design to distinguish agent identities while preserving synchronized temporal coordinates, and injects relative camera geometry into attention to bias overlapping viewpoints toward shared scene evidence. To further strengthen multi-view consistency and enhance global spatial perception, we augment our framework with an overlap-decaying curriculum training paradigm alongside minimap-conditioned structural guidance. To facilitate the training and evaluation of multi-agent models, we introduce PrismaDataset, a large-scale UE5 dataset with panoramic acquisition across diverse scenes, composable multi-agent view groups with flexible agent counts and complex camera trajectories, and precise camera/action annotations for consistency training and evaluation. Experiments show that a single Prisma-World model can generate high-fidelity multi-agent videos with flexible agent numbers, camera controllability, improved cross-view consistency, and spatial grounding under minimap guidance.

2026-06-08T13:59:50Z Project page: https://huiqiang-sun.github.io/prisma-world/ Huiqiang Sun Zhan Peng Size Wu Kun Wang Kang Liao Dianyi Wang Xingyu Zeng Sheng Jin Yangguang Li Zhiguo Cao Ziwei Liu Wei Li http://arxiv.org/abs/2606.07514v1 2026-06-05T17:59:41Z

In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across a continuum of camera systems, from conventional perspective cameras to wide-field-of-view, fisheye and omnidirectional panoramic settings. To overcome the pinhole-specific assumptions of SHARP, our key idea is to align various images in a unified omnidirectional latent space. Thus, we propose UniSHARP, which performs implicit alignment in both feature and Gaussian spaces. Specifically, Gaussian primitives are arranged along rays and radial distances in a ray-based universal representation, while 2D semantic and 3D spatial features extracted from UniK3D-inspired encoders are jointly decoded to generate the complete Gaussian cloud. To comprehensively evaluate our method, we construct a benchmark covering diverse imaging systems across various scenes. The benchmark is further stratified by field of view (FoV) to enable fine-grained assessment of the universal monocular rendering task. Extensive experiments on the proposed benchmark demonstrate the effectiveness of UniSHARP, outperforming alternative methods by a large margin. The project page can be found at: https://insta360-research-team.github.io/Unisharp-website/

2026-06-05T17:59:41Z Project page: https://insta360-research-team.github.io/Unisharp-website/ Meixi Song Dizhe Zhang Hao Ren Ruiyang Zhang Bo Du Ming-Hsuan Yang Lu Qi http://arxiv.org/abs/2606.05067v1 2026-06-03T16:29:15Z

The Deep Graph Generation's panorama spans two extremes: one-shot and sequential models. The former generates nodes and edges jointly, while the latter samples them autoregressively. Each method performs better in different graph domains depending on size and topology, but neither is applicable to all graph categories. For instance, one-shot methods struggle with generating large graphs, while sequential methods underperform on smaller graphs. A possible way to overcome these limitations is to flexibly combine the two methods in a unique system. In this work, we propose the FLAGG (Flexible Autoregressive Graph Generation) framework, which sequentially generates portions of graphs with one-shot models. FLAGG can apply any one-shot model to make it autoregressive, allowing flexibility in choosing the sequential policy. This policy is specified through a stochastic node removal process, which an Insertion Model learns to reverse. We evaluate FLAGG with the DiGress one-shot model on several data sets of different graph sizes and domains. We show that the approach outperforms both one-shot and autoregressive baselines in terms of sampling quality.

2026-06-03T16:29:15Z Accepted for publication at JMLR, currently in press Samuel Cognolato Alessandro Sperduti Luciano Serafini http://arxiv.org/abs/2606.01939v1 2026-06-01T09:04:29Z

Precise 3D representations of industrial environments enable tasks such as robot localization and digital twin generation. We propose SAVMap, a method for generating a semantic wireframe map of warehouse shelf and light structures using only a panoramic video camera as the sensor input. Sequences of rectified images with shelf and ceiling-facing views are extracted from a panoramic video captured along the warehouse aisles. Using a semantic segmentation network front end, a set of sparse, semantic structure feature points (e.g., corners of shelf structures, centers of lights) are extracted from each image and tracked across the sequences. By accounting for real-world geometric relationships among the points such as Manhattan grids, a constrained structure-from-motion algorithm yields the 3D points that form a wireframe map. We demonstrate the scalability and accuracy of our proposal in a warehouse with 46 shelving rows, each with faces spanning 55\,m by 7\,m. From an hour of panoramic video content, we create wireframe maps for over 5000 shelf elements across the rows, achieving an aggregate mean absolute error of 4.8\,cm with respect to ground-truth.

2026-06-01T09:04:29Z IEEE ICRA 2026 Howard Huang Bharath Surianarayanan Keifer Lee Chenyu Wang Chen Feng http://arxiv.org/abs/2606.01186v1 2026-05-31T12:03:19Z

Multi-modal sensing is an important enabler for future environment-aware wireless systems, since a single sensing modality is generally insufficient to provide accurate metric geometry, material awareness, and semantic interpretability in complex environments. This paper presents a measurement-based multi-modal THz sensing and vision framework for indoor environment reconstruction. A three-dimensional monostatic THz channel sounding system operating at 290-310 GHz is integrated with an omnidirectional fisheye camera to acquire radio-frequency and visual observations from a common sensing viewpoint. From the measured THz data, a signal processing pipeline extracts multipath components and infers geometryand material-consistent structural primitives through trajectory tracking-assisted parameter estimation, graph-based structure discovery, planar reconstruction, and reflection-loss analysis. In parallel, AI-based visual perception modules extract object-level semantic masks and depth priors from panoramic images. To associate these heterogeneous representations, an agentic-AI-based task-driven THz-agent module is developed to select appropriate integration tools according to the attributes of the modality-specific outputs. Through angular alignment and consistency analysis, THz-derived metric geometry and material information are associated with vision-derived semantic regions and depth priors, enabling geometry-consistent and semantically interpretable environment reconstruction directly from measurements. Experimental validation in the indoor L-shaped hallway demonstrates that the proposed framework reconstructs dominant structural elements with centimeter-level accuracy while identifying semantic categories and material attributes of representative indoor objects.

2026-05-31T12:03:19Z Yejian Lyu Zitong Fang Zhiqiang Yuan Henk Wymeersch Chong Han http://arxiv.org/abs/2606.00837v1 2026-05-30T18:26:53Z

Diffusion models provide strong priors for generating structured data, but many tasks require outputs beyond the scale on which these models are typically trained. Compositional generation addresses this by composing overlapping local plans from a pretrained short-horizon prior into a long-horizon output. However, standard composition primarily enforces agreement between neighboring local plans, yielding local consistency without directly specifying the global structure of the full composition. As a result, locally compatible plans may still form an implausible route, task sequence, or temporal evolution. Existing methods improve global coherence by repeatedly propagating local consistency signals or by adding inference-time optimization, but these procedures become expensive as the number or dimensionality of local plans increases. We propose Coarse-to-Fine Compositional Diffusion (CoFi), an inference-time sampler that separates global structure formation from local detail refinement. CoFi first aligns local denoised estimates around a shared coarse structure, producing a global scaffold that captures the long-range task-level arrangement. It then diffuses this scaffold to an intermediate noise level and denoises it with the same pretrained local prior, restoring local fine structure while preserving the scaffold-induced global coherence. Across long-horizon robotic planning, panoramic image generation, and long video generation, CoFi not only improves both global coherence and local sample quality over prior compositional baselines, but also requires 2-8x fewer denoiser evaluations.

2026-05-30T18:26:53Z Project page: https://cofi-diffusion.github.io Byoungwoo Park Utkarsh A. Mishra Jaemoo Choi Juho Lee Yongxin Chen http://arxiv.org/abs/2606.07626v1 2026-05-30T15:30:58Z

Perception in dense, unstructured urban traffic remains a major challenge for autonomous driving because of the wide variety of road users, frequent occlusions, irregular motion patterns, and the lack of standardized road layouts. Although recent LiDAR based 3D object detectors have shown strong performance in structured driving scenarios, most are developed and evaluated for limited field of view settings, and their behavior under full surround 360-degree sensing is still not well understood. This paper studies a 360-degree LiDAR perception pipeline for autonomous driving, with particular attention to panoramic sensing, azimuthal sector wise spatial processing, and transformation equivariant feature extraction in complex urban scenes. The paper presents a practical 360-degree perception framework that combines sector wise panoramic processing with rotation equivariant sparse convolutions and evaluates its behavior on a custom Ouster OS0 LiDAR dataset collected across diverse Indian urban traffic conditions. The results show generally stable detection across several object classes, with the strongest performance for cars at 92.02/90.51, buses at 80.53/76.34, and trucks at 78.59/74.16, while lower scores for pedestrians at 67.45/61.02, cyclists at 73.21/69.54, and motorcyclists at 71.20/68.13 reflect the greater difficulty of detecting smaller and more variable road users in dense urban scenes.

2026-05-30T15:30:58Z Pranav Darshan Raghuveer Narayanan Rajesh M Uttara Kumari http://arxiv.org/abs/2605.30940v1 2026-05-29T07:28:24Z

Real-time and accurate spatial audio generation is pivotal for delivering an immersive experience. However, existing spatial audio synthesis technologies are often encumbered by a tradeoff between generation quality and high inference latency, as well as difficulty in capturing precise spatial information from multimodal inputs. To address these challenges, we propose SwanSphere, a unified streaming framework for high-fidelity spatial audio generation from panoramic videos and text prompts. SwanSphere mainly makes the following contributions: 1) We introduce a causal autoregressive diffusion transformer architecture that enables streaming high-quality spatial audio generation. 2) We design a Spatial Video-Audio Contrastive (SVAC) learning strategy to align the video encoder with the acoustic domain, and further employ a multi-objective online direct preference optimization (ODPO) scheme, resulting in strong spatial perception and robust multimodal spatial audio synthesis. 3) To alleviate the current scarcity of spatial audio datasets, we also develop an automated annotation pipeline for generating detailed spatial captions. Experimental results demonstrate that SwanSphere achieves superior performance in both video-to-spatial and text-to-spatial audio generation tasks. Demos can be found at: https://swanaigc.github.io.

2026-05-29T07:28:24Z Accepted by ICML 2026 Ke Lei Yu Zhang Changhao Pan Xueyi Pu Wenxiang Guo Ruiqi Li Zhou Zhao http://arxiv.org/abs/2605.27310v2 2026-09-14T08:22:13Z

Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they reason in language and discard the fine-grained geometry the task requires. Thinking with images aims to fix this by generating an intermediate thinking-image, but recent work shows the visual evidence in these traces is largely ignored. We therefore ask how to make visual thinking matter, and what kind of visual thinking works best. We ask these questions for unified multimodal models (UMMs) that natively support interleaved image-text generation. For the how, we propose View Dropout (VDrop), a training-time intervention that hides parts of one input view from the answer span while leaving it visible to the thinking-image tokens. This incentivizes the model to make use of the thinking-image when answering, rather than answering based on the input views only. With the thinking-image now being used in answer prediction, we ask which kind of visual thinking works best. We frame this as a Learnability-Informativeness (L-I) tradeoff and compare three thinking-image variants: top-down, panoramic, and point-matching renderings. Trained on synthetic scenes and evaluated on five real-world out-of-domain benchmarks, panoramic visual thinking with VDrop is the only configuration that is simultaneously informative and learnable, and achieves the best out-of-domain generalization.

2026-05-26T17:20:05Z Accepted at EMNLP 2026 Main Conference. Code available at https://github.com/MyLittleChange/VDrop Qian Yang Ankur Sikarwar Huy Le Le Zhang Zhuan Shi Perouz Taslakian Aishwarya Agrawal http://arxiv.org/abs/2605.26447v1 2026-05-26T02:01:06Z

Underwater scene reconstruction is essential for immersive exploration of aquatic environments, yet remains challenging due to complex participating-media effects such as absorption and scattering, as well as the limited field of view (FoV) of conventional cameras. Although combining panoramic imaging with 3D Gaussian Splatting (3DGS) offers a promising direction for photorealistic underwater rendering, traditional 3DGS struggles with both spherical projection distortion and underwater medium degradation. In this paper, we propose \textbf{Underwater360}, a physics-informed omnidirectional 3DGS framework for underwater panoramic scene reconstruction. First, we introduce an Omnidirectional Gaussian Splatting module that performs ray casting directly in spherical camera space instead of relying on 2D projection approximations, thereby reducing geometric distortions under 360$^\circ$ FoV. Second, we design a physics-based appearance-medium modeling architecture with pose-conditioned appearance embeddings to explicitly decouple intrinsic scene radiance from depth-dependent backscatter and attenuation, enabling physically grounded scene appearance restoration. Finally, we establish a new panoramic underwater benchmark dataset containing both synthetic and real-world scenes. Extensive experiments demonstrate that Underwater360 achieves superior performance in underwater novel view synthesis and scene appearance restoration, delivering improved rendering quality and cross-view consistency in complex underwater environments. The code and datasets are released at https://github.com/SwcK423/Underwater360

2026-05-26T02:01:06Z Jiangbei Hu Weichao Song Shibo Yu Mohan Wang Zihan Yi Rui Wu Mingkang Xiang Na Lei Shengfa Wang Zhongxuan Luo Ying He http://arxiv.org/abs/2605.25449v3 2026-06-15T08:38:54Z

Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constraints that remain challenging for perspective video generators due to their limited field of view (FoV). Their narrow FoV forces long or multi-view trajectories, amplifying cross-view inconsistency and temporal drift. We argue that 360° video generation offers a natural solution: panoramic coverage simplifies trajectory design and provides a strong global context for maintaining coherence. We introduce Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion, a controllable 360° video generation framework that synthesizes high-fidelity videos from sparse 360° inputs. The key idea is an explicit 3D Cache, reconstructed from the input, which serves as a geometric scaffold for any user-defined camera path. This allows the diffusion model to focus on photorealistic texture refinement while the 3D Cache enforces global geometric consistency. Experiments show that Pantheon360 achieves superior visual quality and unmatched geometric coherence, enabling reliable and flexible 360° scene generation for downstream simulation and digital-twin applications.

2026-05-25T06:00:01Z Accepted to CVPR 2026. Project page: https://koi953215.github.io/pantheon360_page/ Ting-Hsuan Chen Ying-Huan Chen Tao Tu Jie-Ying Lee Cho-Ying Wu Fangzhou Lin Hengyuan Zhang David Paz Xinyu Huang Yuliang Guo Yu-Lun Liu Yue Wang Liu Ren http://arxiv.org/abs/2605.19974v1 2026-05-19T15:19:16Z

The generation of immersive and navigable 3D environments is increasingly prevalent with the growing adoption of virtual reality and 3D content. However, recent methods face a fundamental limitation: they cannot produce 3D worlds that simultaneously (i) are navigable over long-range spatial extents and (ii) cover the complete omnidirectional field of view ($360^\circ$ horizontally and $180^\circ$ vertically). To address this challenge, we introduce SphericalDreamer, a method for generating fully immersive and long-range 3D outdoor environments from textual prompts. Our approach is built on the generation of multiple panoramic images, which are subsequently lifted into 3D and fused together while maintaining visual and geometric consistency. SphericalDreamer produces highly detailed, fully immersive 3D environments, while substantially improving scale and navigability compared to prior approaches.

2026-05-19T15:19:16Z Accepted at ICML 2026. Project page available at https://sphericaldreamer.github.io Antoine Schnepf Karim Kassab Flavian Vasile Andrew Comport http://arxiv.org/abs/2605.17916v2 2026-05-19T02:30:02Z

Generating a consistent whole-house VR tour from a floorplan and style reference requires both photorealistic panoramas and cross-view spatial coherence. Pure 2D generators produce appealing single panoramas but re-imagine geometry and materials when the viewpoint changes, whereas monolithic 3D generation becomes expensive and loses fine texture at multi-room scale. We introduce PanoWorld, a generative spatial world model that treats whole-house synthesis as autoregressive generation of node-based 360-degree panoramas, matching the discrete navigation used by real VR tour products. PanoWorld uses a floorplan-derived 3D shell as a global geometric proxy and a dynamic 3D Gaussian Splatting cache as renderable spatial memory. A feed-forward panoramic LRM designed for metric-scale multi-room 360-degree inputs lifts generated panoramas into local 3DGS updates, while Room-aware Group Attention suppresses cross-room feature interference. A topology-aware progressive caching strategy fuses these local updates without repeatedly reconstructing the full history. By decoupling shell-based geometry guidance from cache-rendered visual memory, PanoWorld preserves high-frequency 2D synthesis quality while improving cross-node layout and material consistency. The project link is https://jjrcn.github.io/PanoWorld-project-home/

2026-05-18T06:25:37Z 17 Jinrang Jia Zhenjia Li Yijiang Hu Yifeng Shi http://arxiv.org/abs/2605.17804v2 2026-05-19T06:01:06Z

Generative models have demonstrated remarkable potential in time series analysis tasks, like synthesis, forecasting, imputation, etc. However, offering limited coverage for generative models, existing time series libraries are mainly engineered for discriminative models, with standardized workflows for specific tasks, such as optimizing Mean Squared Errors for time series forecasting. This rigid structure is fundamentally incompatible with the distinct and often complex paradigms of generative models (e.g., adversarial training, diffusion processes), which learn the underlying data distribution rather than a direct input-output mapping. To this end, we proposed GenTS, a comprehensive and extensible benchmark library designed for systematic assessment on generative time series models. GenTS features a unified data preprocessing pipeline, a collection of versatile models, and panoramic evaluation metrics. Its modular design also enables the researchers to flexibly customize beyond our built-in datasets and models. Based on GenTS, we conducted benchmarking experiments under diverse tasks, accordingly offering suggestions for model selection and identifying potential directions for future research. Our codes are open-source at https://github.com/WillWang1113/GenTS. The official tutorials and document are available at https://willwang1113.github.io/GenTS/.

2026-05-18T03:27:54Z Chenxi Wang Xiaorong Wang Peiyang Li Yi Wang http://arxiv.org/abs/2605.15391v1 2026-05-14T20:24:23Z

We present PanoWorld, a panoramic video world model that generates geometry-consistent 360$\degree$ video from a single image and a caption. Existing panoramic video methods optimize primarily for visual realism and do not explicitly constrain the underlying 3D scene state, producing outputs that appear plausible yet exhibit inconsistent depth, broken correspondences, and implausible motion across the spherical surface. We address this gap by framing panoramic video generation as a geometry- and dynamics-consistent latent state modeling problem rather than pure visual synthesis. Building on a pre-trained perspective video world model, we introduce two lightweight regularizers: a depth consistency loss against pseudo ground-truth panoramic depth, and a trajectory consistency loss that supervises the 3D world-frame positions of tracked points across time. We further apply spherical-geometry-aware adaptation to the conditioning and positional encoding. We additionally introduce PanoGeo, a unified geometry-aware panoramic video dataset with consistent depth, trajectory, and prompt annotations across diverse real and synthetic sources, used for both training and stratified evaluation. Experiments show that PanoWorld improves geometric consistency over prior panoramic generation methods while maintaining competitive visual realism, establishing that panoramic video generation must be treated as a geometric modeling problem to support the holistic spatial understanding requirements of embodied AI applications. Code is available at https://github.com/ostadabbas/PanoWorld.

2026-05-14T20:24:23Z Le Jiang Xiangyu Bai Bishoy Galoaa Shayda Moezzi Caleb James Lee Tooba Imtiaz Edmund Yeh Jennifer Dy Yanzhi Wang Sarah Ostadabbas http://arxiv.org/abs/2605.14963v2 2026-05-16T11:48:36Z

Stereo matching on top-bottom equirectangular images provides an effective framework for full-surround perception, as vertically aligned epipolar lines enable the use of advanced perspective stereo architectures that are largely driven by large-scale datasets and monocular priors. However, the performance of such adaptations is severely limited by the scarcity of omnidirectional stereo datasets and the degradation of perspective monocular priors under spherical distortions. To address these challenges, we propose H-OmniStereo, a zero-shot omnidirectional stereo matching framework. First, we construct high-quality synthetic dataset comprising over 2.8 million top-bottom equirectangular stereo pairs to scale up training. Second, we introduce an equirectangular monocular normal estimator, specifically operating in a heading-aligned coordinate system. Beyond providing distortion-robust and cross-view-consistent geometric priors for establishing reliable correspondences in stereo matching, this design boosts training efficiency and accommodates train-test FoV mismatches. Extensive experiments show that our approach achieves higher accuracy than existing methods on out-of-domain datasets and successfully generalizes to real-world consumer camera setups using a single model. The model and dataset will be released at https://github.com/JIANG-CX/H-OmniStereo.

2026-05-14T15:30:22Z 8 pages, 9 figures Chenxing Jiang Zhe Tong Pusen Gao Peize Liu Yang Xu Chuan Fang Ping Tan Shaojie Shen http://arxiv.org/abs/2605.16420v1 2026-05-14T12:38:23Z

This paper addresses the problem of reconstructing missing or dropped frames in top-down drone video of autonomous surface vehicles performing structured maritime manoeuvres. We propose a pipeline that converts raw GPS telemetry and a single reference frame into a trajectory-guided video sequence using a pre-trained image-to-video diffusion model, requiring no domain-specific fine-tuning. GPS coordinates from onboard telemetry logs are projected into image space via an equirectangular mapping, producing per-vessel motion cues that condition the SG-I2V diffusion model. The generated frames are evaluated against ground-truth video using perceptual, temporal and trajectory-based metrics, and benchmarked against optical flow extrapolation and RIFE interpolation baselines. SG-I2V produces the most naturally appearing frames among all methods (BRISQUE 25.52, closest to ground-truth 23.64), the most realistic motion magnitude (temporal smoothness 1.14 vs. ground truth 1.42), and the strongest GPS trajectory adherence (9.31px vs. 28.70px for ground-truth, the latter reflecting approximate temporal alignment between footage and GPS logs rather than generation error), demonstrating that trajectory-guided diffusion synthesis is a viable approach to maritime video reconstruction under challenging low-texture, small-object conditions.

2026-05-14T12:38:23Z Accepted at the 1st Workshop on Multi-Sensor Trajectory Knowledge Discovery and Extraction (MuseKDE 2026), co-located with the 27th IEEE International Conference on Mobile Data Management (IEEE MDM 2026) Stelio Bompai Ioannis Kontopoulos Giannis Spiliopoulos Dimitris Zissis Konstantinos Tserpes http://arxiv.org/abs/2605.14601v1 2026-05-14T09:14:24Z

Three-dimensional object detection in panoramic imagery is crucial for comprehensive scene understanding, yet accurately mapping 2D features to 3D remains a significant challenge. Prevailing methods often project 2D features onto discrete 3D grids, which break geometric continuity and limit representation efficiency. To overcome this limitation, this paper proposes PanoGSDet, a monocular panoramic 3D detection framework built upon continuous semantic 3D Gaussian representations. The proposed framework comprises a panoramic depth estimation component and a semantic Gaussian component. The panoramic depth estimation component extracts the equirectangular semantic and depth features from the monocular panorama input. The semantic Gaussian component includes a semantic Gaussian lifting module that projects spherical features into 3D semantic Gaussians, a semantic Gaussian optimization module that refines these semantic Gaussians, and a Gaussian guided prediction head that generates 3D bounding boxes from optimized Gaussian representations. Extensive experiments on the Structured3D dataset demonstrate that our method significantly outperforms existing methods.

2026-05-14T09:14:24Z Current has been accepted by ICME 2026 Kanglin Ning Yiran Zhao Wenrui Li Shaoru Sun Xingtao Wang Xiaopeng Fan http://arxiv.org/abs/2605.14135v1 2026-05-13T21:39:01Z

We present PanoPlane, an approach for high-fidelity sparse-view indoor novel view synthesis that reconstructs closed room geometry via panoramic scene completion. Unlike perspective-based methods that generate training views from limited fields of view, PanoPlane leverages $360^{\circ}$ panoramic completion to condition the generative process on the full spatial layout. We propose Layout Anchored Attention Steering, a training-free mechanism that steers attention within the diffusion model's internal representation toward scene's detected planar surfaces at inference time. By directing each unobserved region's attention toward geometrically consistent observed content, our method replaces unconstrained hallucination with grounded surface extrapolation. The resulting panoramic completions provide supervision for 3D Gaussian Splatting, enabling accurate novel-view synthesis across unobserved regions from as few as three input views. Experiments on Replica, ScanNet++, and Matterport3D demonstrate state-of-the-art novel view synthesis quality across 3, 6, and 9 input views, achieving up to $+17.8\%$ improvement in PSNR over the current state-of-the-art baseline without any training or fine-tuning of the diffusion model.

2026-05-13T21:39:01Z Adil Qureshi Dongki Jung Jaehoon Choi Dinesh Manocha http://arxiv.org/abs/2605.11115v1 2026-05-11T18:24:04Z

High Dynamic Range (HDR) generation remains challenging for generative models, which are largely limited to low dynamic range outputs. Recent diffusionbased approaches approximate HDR by generating multiple exposure-conditioned samples, incurring high computational cost and structural inconsistencies across exposures. We propose LatentHDR, a framework that decouples scene generation from exposure modeling in latent space. A pretrained diffusion backbone produces a single coherent scene representation, while a lightweight conditional latent to-latent head deterministically maps it to exposure-specific representations. This enables the generation of a dense, structurally consistent exposure stack in a single pass. This design eliminates multi-pass diffusion, ensures cross-exposure alignment, and enables scalable HDR synthesis. LatentHDR supports both textand image-conditioned HDR generation for perspective and panoramic scenes. Experiments on synthetic data and the SI-HDR benchmark show that LatentHDR achieves state-of-the-art dynamic range with competitive perceptual quality, while reducing computation by an order of magnitude. Our results demonstrate that high-quality HDR generation can be achieved through structured latent modeling, challenging the need for stochastic multi-exposure generation.

2026-05-11T18:24:04Z Pedram Fekri WenChen Li William Chen Peter Altamirano http://arxiv.org/abs/2605.01333v2 2026-05-08T01:08:56Z

Multimodal large language models (MLLMs) have emerged as a promising paradigm for dental image analysis. However, their ability to capture the multi-level cognitive processes required for radiographic analysis remains unclear. Here, we present a comprehensive benchmark to evaluate the cognitive capabilities of MLLMs in dental radiographic analysis. It spans three critical imaging modalities, i.e., periapical, panoramic, and lateral cephalometric radiographs, and defines four cognitive categories: perception, comprehension, prediction, and decision-making. The benchmark comprises 27 clinically grounded tasks derived from public datasets, with manually curated annotations and 3,820 clinician assessments for evaluation. Six frontier MLLMs, including GPT-5.2 and GLM-4.6, are evaluated. We demonstrate the performance gap between MLLMs and clinicians in dental practice, delineate model strengths and limitations, characterize failure patterns, and provide recommendations for improvement. This data resource will facilitate the development of next-generation artificial intelligence systems aligned with clinical cognition, safety requirements, and workflow complexity in dental practice.

2026-05-02T09:08:33Z 21 pages, 4 figures, 5 tables Rongyang Wang Shuang Zhou Jiashuo Wang Wenya Xie Xiaoxia Che http://arxiv.org/abs/2604.23953v1 2026-04-27T01:58:37Z

Blind omnidirectional image quality assessment (BOIQA) presents a great challenge to the visual quality assessment community, due to different storage formats and diverse user viewing behaviors. The main paradigm of BOIQA models includes two steps, ie, viewport generation, and quality prediction, which brings an extra computational burden and is hard to generalize to other visual contents (eg, 2D planar image). Thus, in this paper, we make an attempt to solve these issues. First, we experimentally find that BOIQA can be formulated as a blind (2D planar) image quality assessment (BIQA) problem, ie, the first step - viewport generation - is no longer needed, which narrows the natural gap between BOIQA and BIQA. Then, we present a new BOIQA approach, which has three merits: ie, viewport-unaware - it accepts an omnidirectional image in the widely used equirectangular projection format as input without any transformation; unified - it can also be applied to BIQA; and generalized - it shows better generalizability against other competitors. Finally, we validate its promise by held-out test, cross-database validation, and the well-established gMAD competition.

2026-04-27T01:58:37Z Jiebin Yan Kangcheng Wu Jingwen Hou Jiayu Zhang Pengfei Chen Yuming Fang