https://arxiv.org/api/NNFt8lIY8apw5/gpOrAABGBAZts 2026-09-27T19:38:41Z 200 55 0 http://arxiv.org/abs/2609.30234v1 2026-09-24T17:53:55Z

Automated generation of production-ready 3D garment assets from a single image is a central challenge in digital content creation. While recent generative models have significantly advanced 3D geometry reconstruction, synthesizing high-quality textures remains a bottleneck. Existing methods often bake environmental illumination and shadows directly into the texture map, or they fail to maintain global structural coherence, making the resulting assets unusable for physical simulation and relighting. In this work, we introduce OmniFabric, a novel approach that synthesizes globally coherent texture maps directly within the 2D sewing pattern space. Given a single reference image, our pipeline utilizes an estimated 3D mesh and generative priors of powerful Vision-Language Models (VLM) to establish a complete but coarse texture initialization across the unwrapped sewing patterns. We then leverage a specialized diffusion transformer, trained via an automated synthetic data engine and conditioned on 3D positional features, to refine this initialization directly in the canonical UV domain. This effectively removes distortion and baked-in artifacts to extract a clean and normalized texture map that preserves the original garment design. Extensive experiments demonstrate that OmniFabric significantly outperforms state-of-the-art baselines, yielding photorealistic 3D garments with high-quality textures.

2026-09-24T17:53:55Z Accepted to SIGGRAPH Asia 2026. Project Page: https://humansensinglab.github.io/OmniFabric/ Ding-Jiun Huang Yuanhao Wang Cheng Zhang Hugo Bertiche Alexandru-Eugen Ichim Thabo Beeler Fernando De la Torre http://arxiv.org/abs/2609.29985v1 2026-09-24T15:35:08Z

Underwater 3D reconstruction is critical for marine exploration, ecological monitoring, and subsea infrastructure inspection, yet remains challenging at large scale due to light attenuation, scattering, and limited capture coverage. While 3D Gaussian Splatting (3DGS) enables high-quality real-time rendering, its application to large underwater scenes is constrained by high memory consumption and inefficient optimization over extensive areas. We propose OceanXL, a fast and scalable 3DGS-based framework for large-scale underwater reconstruction. OceanXL adopts a divide-and-conquer strategy, partitioning scenes into spatially coherent blocks to enable efficient optimization while preserving global geometric consistency. We further introduce an adaptive pruning scheme tailored to underwater conditions that removes redundant primitives, producing compact representations without sacrificing visual fidelity. Together, these components improve training efficiency and rendering performance for large scenes. We also introduce a large-scale underwater dataset covering diverse marine environments. Experiments on five large-scale scenes demonstrate favorable scalability, compactness, and efficiency--quality trade-offs over large-scene baselines. Controlled comparisons on the small-scale SeaThru-NeRF dataset further show competitive reconstruction quality with substantially smaller model sizes than underwater-specific methods.

2026-09-24T15:35:08Z SIGGRAPH ASIA 2026 Haoran Wang Shaoyu Cai Adrian Azzarelli Zhuodong Jiang Guoxi Huang Eng Tat Khoo Brett Seymour Fan Zhang David Bull Nantheera Anantrasirichai http://arxiv.org/abs/2609.27560v1 2026-09-23T08:45:40Z

Avatar-streaming systems are commonly evaluated with image and video quality assessment (IQA/VQA) metrics, implicitly treating visual fidelity as a proxy for communicative success. We test this assumption through a controlled behavioral study of rendered 3D avatars across a pristine condition and fourteen geometric, photometric, temporal, and combined distortions. Fifty-nine participants contributed 2,688 judgments of perceived action, response confidence, and visual quality. We identify Misleading Quality in this dataset as distorted renderings that retain above-average perceived quality but yield below-average action-recognition accuracy. We also derive an Intent Quality Score (IQS) combining recognition correctness and confidence as the behavioral target for objective metrics. Among 126 distorted content--condition cells, 31 (24.6%) exhibited Misleading Quality; temporal and geometric distortions showed the highest rates, at 50.0% and 31.1%, respectively. The results reveal a quality--accuracy dissociation where distortion families affect appearance and communication differently. Across 24 direct-scoring IQA/VQA metrics and three supervised feature-regression baselines, alignment with IQS remained limited; at $λ=0.5$, the best leave-one-content-out baseline reached PLCC $=0.4435$. Under this controlled protocol, visual fidelity alone is insufficient for avatar communication, motivating intent-aware quality assessment and streaming objectives.

2026-09-23T08:45:40Z Accepted to SIGGRAPH Asia 2026 Technical Communications. 6 pages Ning-Hsuan Chang Kai-Siang Ma Yu-Chih Chen 10.1145/3829339.3847861 http://arxiv.org/abs/2609.28539v1 2026-09-22T21:25:20Z

Gaussian head avatars typically model intrinsic facial appearance as temporally static, omitting subtle cardiac-induced skin-color variation. We propose $\unicode{x1F493}$Heartian, a physiology-aware modulation framework that learns cardiac-cycle-dependent per-frame albedo modulation of facial skin-region Gaussians within a relightable head avatar to encode remote photoplethysmography (rPPG) signals. Using synchronized contact PPG supervision, $\unicode{x1F493}$Heartian models the prescribed cardiac waveform as the sum of two Gaussian functions and learns per-frame spatial residuals via a lightweight MLP. Across 152 stationary recordings from UBFC-rPPG, PURE, and MMPD, attribute-space recovery of the supplied signal achieves a pooled recording-level heart-rate MAE of 0.29 bpm and MAPE of 0.38%. The signals remain detectable after rendering by benchmark rPPG methods, with the best tested configuration - a motion-augmented TS-CAN decoder pretrained on UBFC-rPPG - recovering heart rate from the rendered MMPD avatars at 0.97 bpm MAE and 1.21% MAPE. Meanwhile, $\unicode{x1F493}$Heartian maintains reconstruction quality comparable to the baseline, with negligible average PSNR degradation of 0.005 dB. Overall, our work embeds recoverable rPPG signals as controllable material attributes to subject-specific Gaussian head avatars while retaining the reconstruction quality.

2026-09-22T21:25:20Z 4 pages of manuscript and 2 pages of supplementary material; SIGGRAPH Asia 2026 Technical Communications Xiaoyue Fan Jose Echevarria Akshay Paruchuri Kaan Akşit 10.1145/3829339.3847838 http://arxiv.org/abs/2609.25832v1 2026-09-22T07:58:27Z

Part segmentation is a fundamental problem in computer graphics and 3D vision. Recent works have expanded 3D part segmentation beyond fixed taxonomies, but existing approaches typically only address a specific setting, such as text-guided part segmentation or point-based interaction. In this work, we argue that these settings can be unified as an intent-conditioned generative problem, where different prompts specify the desired part decomposition. To this end, we introduce PartLLM, a unified multimodal model that formulates 3D part segmentation as autoregressive semantic decomposition. Conditioned on an input shape and a user prompt, PartLLM autoregressively generates semantic part hypotheses as queries for mask prediction and feeds them to a decomposition-aware decoder that jointly predicts coherent part masks. This unified design supports text-guided part segmentation, interactive segmentation, and full-shape semantic decomposition with controllable granularity within a single model. Extensive experiments across these task settings show that PartLLM consistently outperforms task-specific baselines, demonstrating the effectiveness of unifying 3D part segmentation under an intent-conditioned generative formulation.

2026-09-22T07:58:27Z Accepted to SIGGRAPH Asia 2026 (ACM Transactions on Graphics). Project Page: https://czvvd.github.io/PartLLMPage/ Zhe Zhu Yiheng Zhang Peng Li Zixing Zhao Honghua Chen Yaqing Zhang Le Wan Zhiyang Dou Cheng Lin Yuan Liu Mingqiang Wei Wenping Wang http://arxiv.org/abs/2609.24025v1 2026-09-21T02:47:59Z

We present a method for synthesizing reactive character behaviors for continuous games as compact, human-readable programs. Game AI practice still relies heavily on manually authored behavior trees, state machines, and scripts, while academic reinforcement learning typically produces opaque neural controllers that are expensive to train and difficult to edit. Our approach bridges this gap by searching directly over a domain-specific language for continuous-space game policies. The language is designed around reactive geometric decisions and includes higher-order constructs such as direction maximization. These constructs help discretize a continuous behavior space into enumerable program structures. To make program search practical, we introduce a large set of synthesis antipatterns that remove redundant program forms while preserving behavioral coverage. We further combine bottom-up symbolic enumeration with top-down guidance from a coding agent. Our resulting method, agentic sketching, has the agent propose high-level policy structure and call an enumerator to complete local program slots. We evaluate the method on a benchmark of 14 continuous games, ranging from classic control tasks to multi-agent football. We find that pure enumeration is often more efficient than using a coding agent alone, while the combined method substantially outperforms both. Our results suggest that programmatic policy search can be a practical authoring tool for game AI: designers specify reward functions, and the system discovers editable behaviors that are effective, portable, and often surprising.

2026-09-21T02:47:59Z To be presented at SIGGRAPH Asia 2026 Maxim Gumin Hsueh-Ti Derek Liu Victor Zordan Daniel Ritchie 10.1145/3829340.3842379 http://arxiv.org/abs/2609.20524v1 2026-09-17T15:02:45Z

Rigid-body interpenetration frequently occurs in procedurally assembled and generated scenes and must be removed before downstream applications such as physical simulation. We present S4R (Scaling for Rigid-Body Interpenetration Resolution), a scale-continuation method for static interpenetration repair. S4R first uniformly shrinks each body about a fixed reference center to a small initial scale, at which the layout is penetration-free, and then restores full scale through a sequence of minimum-norm convex contact quadratic programs (QPs) that target the linearized separation margin during continuation. Resolution thereby replaces one deep correction with a sequence of shallow-contact subproblems. A conservative scale-event bound and frozen-witness gap predictions cut the number of exact mesh queries; the continuation then ends with a full-scale evaluator check and bounded tail refinement. We evaluate S4R on Kubric, HY3D-Bench, and Thingi10K using a shared mesh-level evaluator and a unified per-scene timing protocol. In the main comparisons on all three benchmarks, up to N=5000 bodies, S4R reaches zero reported penetration with displacement that stays small and nearly independent of scene size, and at the lowest wall time within each hardware tier among the compared methods. A GPU implementation extends these results to large-scale scenes. Our code and data can be found on our project page: https://frank-zy-dou.github.io/projects/S4R/index.html.

2026-09-17T15:02:45Z ACM Transactions on Graphics 45(6), Article 197 (SIGGRAPH Asia 2026). Project page: https://frank-zy-dou.github.io/projects/S4R/index.html Zhiyang Dou Ang Zhao Chen Peng Minghao Guo Haixu Wu Cheng Lin Yuan Liu Junfeng Yao Xiaohu Guo Wenping Wang Wojciech Matusik 10.1145/3842510 http://arxiv.org/abs/2609.19872v1 2026-09-17T08:23:25Z

3D assembly is fundamental to modern manufacturing and digital content creation. In this paper, we present PART, a unified transformer-based framework for 3D part retrieval and assembly: given a target shape and a part library, PART automatically selects the appropriate parts and predicts their 6-DoF poses to reconstruct the target. While prior work has achieved impressive progress on assembling a pre-defined set of parts, this more practical retrieval-based setting remains largely unexplored. The task faces three key challenges: (i) a combinatorially explosive search space that grows exponentially with library size; (ii) variable-length outputs, as different targets require different numbers of parts; and (iii) continuous 6-DoF pose estimation for part assembly. To address these, we formulate retrieval and assembly as a set prediction problem and design a novel transformer-based framework that retrieves parts and regresses their poses with variable-length output. Additionally, we exploit the duality between part pose estimation and target segmentation through joint training and a novel segmentation-enhanced optimization module. Finally, We curate a large-scale dataset of 80K+ shapes, and the results show that PART generalizes to scene layouts, image targets, and real-world scans. Project Page: https://iambrc.github.io/PART-project-page/.

2026-09-17T08:23:25Z Accepted to SIGGRAPH Asia 2026 Conference Papers. 11 pages, 12 figures. Project page: https://iambrc.github.io/PART-project-page/ Ruchao Bao Wenzheng Wu Chucheng Xiang Zhongyuan Liu Yuan Liu Jinxin Dong Ligang Liu Ziqi Wang http://arxiv.org/abs/2609.16603v2 2026-09-17T02:27:15Z

Full-context neural visual geometry is impractical for thousands of images, while sequence-based chunking poorly captures irregular non-local overlap in multi-sequence aerial collections. We present Graph-Guided Neural Visual Geometry for Aerial Registration (G3AR), a graph-guided framework for scalable dense neural geometry. Before local inference, G3AR builds a geometrically verified image-proximity graph that guides bounded overlapping chunks and induces a chunk graph whose maximum spanning tree defines alignment topology. Compatible backbones process chunks independently; shared-image predictions then estimate three-dimensional similarity (Sim(3)) transforms that register local cameras and geometry in a common frame. Across four real aerial scenes, G3AR improves pose error and runtime in matched VGGT- and Pi3-backed comparisons, while its DA3 variant achieves the lowest pose error among evaluated neural-geometry methods.

2026-09-15T03:58:17Z 6 pages, 4 figures, 8 tables. Accepted to SIGGRAPH Asia 2026 Technical Communications. Code: https://github.com/Joshimello/g3ar Jeng Wen Joshua Lean Ting-Yu Yen Wei-Fang Sun Simon See Hung-Kuo Chu Shih-Hsuan Hung 10.1145/3829339.3847824 http://arxiv.org/abs/2609.14521v1 2026-09-13T13:56:44Z

Recovering editable 3D parametric curves from 2D images is a fundamental challenge in computer graphics, bridging pixel-based perception and vector-based CAD modeling. Existing NeRF- and 3DGS-based methods often rely on dense calibrated views, precomputed 2D edge maps, and costly per-scene optimization, limiting their applicability to casually captured real-world inputs. We propose CGGT, a Curve-Grounded Geometry Transformer that directly grounds 3D-consistent 2D curve instances in the image space from sparse, unposed multi-view images. CGGT combines a geometry-aware transformer encoder for multi-view feature learning with a curve-aware masked-attention decoder for cross-view instance association. In a single forward pass, it predicts camera parameters, dense depth maps, and instance-level 2D curve masks, which are then lifted into 3D and refined through a fast parametric optimization stage to recover compact, editable 3D curve primitives. To support structured curve learning, we introduce Wireframe-100K, a large-scale dataset comprising 100,000 CAD models with diverse topologies, realistic multi-view renderings, and accurate parametric curve annotations. Extensive experiments show that our framework achieves substantial improvements in both reconstruction accuracy and efficiency, particularly under challenging sparse-view settings and in separating persistent 3D structural edges from view-dependent image edges caused by silhouettes, textures, and appearance variations. Despite being trained solely on synthetic data, CGGT generalizes well to real-world images, demonstrating its potential for practical CAD-style wireframe reconstruction from unconstrained visual inputs.

2026-09-13T13:56:44Z Accepted by SIGGRAPH Asia 2026 Zhirui Gao Renjiao Yi Yunfan Ye Ruizhen Hu Chenyang Zhu Wei Chen Kai Xu http://arxiv.org/abs/2609.13135v1 2026-09-11T17:56:16Z

We present an approach to progressively extend the highlights of an image. Instead of reconstructing the full dynamic range of a complex scene directly, we learn a simpler task first: We extend the dynamic range of an input image by a single exposure value. Once this is mastered, we retrieve the full HDR image for the scene by executing our network recurrently, progressively increasing the dynamic range of the input. Our formulation is agnostic to the input dynamic range and targets a bounded output domain. This enables us to use widely available RAW images for the reconstruction task and adapt adversarial losses to construct realistic images. By incorporating Memory Replay for backpropagation, we can train our network recurrently over multiple inference stages and reduce reconstruction errors. As a consequence, our system reconstructs challenging long-tailed HDR scenes robustly and shows powerful recovery of bright light sources and highlights.

2026-09-11T17:56:16Z 10 pages, 8 figures. Accepted to ACM SIGGRAPH Asia 2026 Sebastian Dille Keru Fu S. Mahdi H. Miangoleh Yağız Aksoy http://arxiv.org/abs/2609.12342v1 2026-09-11T02:08:54Z

The conditional generation of 3D motion has emerged as a key research topic due to its wide applicability across robotics, AR/VR, gaming, and content creation. However, extending recent advances in text-driven human motion generation to the animal domain remains challenging due to two core limitations. First, animals exhibit highly diverse skeletal topologies, unlike the standard human structure, making unified modeling across species difficult and leading to inefficient per-species models. Second, existing animal motion datasets suffer from limited scale and annotation quality, constraining model performance. To address these challenges, we propose UniMo, a unified point cloud-based motion generation framework that bypasses topological discrepancies by converting parametric skeletons into unparametric representations, further enhanced by dynamic sampling that allocates more points to active joints. Additionally, we present UniML3D, a large-scale motion-language dataset spanning both human and animal categories, containing 145,907 motion sequences and 433,388 captions-over 102x larger than existing animal datasets. Our method achieves state-of-the-art results on UniML3D and three public benchmarks including HumanML3D, KIT-ML, and AnimalML3D, demonstrating the feasibility and effectiveness of unified human-animal motion generation. Website: https://steve-zeyu-zhang.github.io/UniMo.

2026-09-11T02:08:54Z Accepted to SIGGRAPH Asia 2026 Posters Zeyu Zhang Zhiyuan Zhang Siheng Wang Yiran Wang Danning Li Ian Reid Richard Hartley http://arxiv.org/abs/2609.11434v1 2026-09-10T12:06:11Z

We introduce Complex-Valued Quadratic Phase Gaussian (CVQPG), a novel hologram representation method that replaces standard 2D Gaussian representations used in 2D Gaussian Splatting with 2D quadratic phase functions. CVQPG incorporates additional learnable parameters to control the curvature of these bases. We evaluate our approach against state-of-the-art methods, exceeding the visual quality by +0.19 dB (RGB) and +0.33 dB (grayscale) on average in holographic reconstructions. Specifically, our equal parameter count evaluations show that modulating the primitive's wavefront is an effective and lightweight enhancement for hologram representations. In addition, our frequency domain analysis illustrates that CVQPG has successfully preserved the mid-to-high frequency band of natural images.

2026-09-10T12:06:11Z SIGGRAPH Asia 2026 Technical Communications Haolong Wang Yicheng Zhan Kaan Akşit Simeng Qiu http://arxiv.org/abs/2609.11430v1 2026-09-10T12:03:05Z

We present a novel method for computing global illumination by expressing the solution to the light transport equation as a 13D Gaussian mixture model over positions, directions, surface normals, and material properties. We show that including scene properties in the Gaussian representation drastically reduces the number of functions and speeds up evaluation. As opposed to traditional light transport methods based on Neumann series, the parameters of our model are directly estimated by minimizing the residual of the rendering equation. While both optimization and rendering require repeated evaluations of a linear combination of high-dimensional Gaussian functions, we introduce an efficient culling strategy to keep the optimization tractable and produce renderings in real time. Our representation enables to render fast, view-independent solutions to the light transport equation, achieving rendering times on the order of milliseconds, with a fraction of the memory requirements of conventional neural rendering approaches.

2026-09-10T12:03:05Z To appear in SIGGRAPH Asia 2026 (Conference Track). 11 pages, 8 figures. Project page: https://patrick-attimont.com/projects/gaussian-light-transport/ Patrick Attimont Kartic Subr Cyril Soler http://arxiv.org/abs/2609.10982v1 2026-09-10T02:01:55Z

We present ReCHOIR, a novel contact-guided motion retargeting method for transferring human object interaction (HOI) motions across diverse humanoid characters. Unlike prior motion retargeting methods that primarily focus on transferring human motion alone, our goal is to preserve not only the semantics of the original body movement but also consistent interaction between the character and the manipulated object, while jointly producing aligned target human and object motions. Given source HOI motion, object geometry, and contact cues extracted from the source interaction, ReCHOIR retargets an HOI sequence to target characters with different skeletal configurations while maintaining both motion semantics and contact-consistent interaction patterns. Our method builds on a Part-Aware Motion Embedding (PAME) autoencoder, which encodes full-body motion into a shared body-part-wise latent space. This representation enables generalization across heterogeneous skeletons while preserving local motion semantics beneficial for part-aware adaptation in HOI retargeting. On top of this representation, we introduce a contact-guided retargeting module and an object motion decoder for HOI retargeting. The contact-guided retargeting module treats the source object interaction as a condition for refining target character motion: object- and contact-related signals are encoded into a body-part-aligned latent representation and injected into decoding through a residual control branch, enabling stronger adaptation in interaction-relevant body regions without discarding the underlying motion prior. In parallel, the object motion decoder predicts a target object motion aligned with the refined target character motion, ensuring that the object trajectory remains consistent with how the interaction is realized by the target character.

2026-09-10T02:01:55Z SIGGRAPH Asia 2026 (Journal Track). Project page: https://cherry-leki.github.io/projects/ReCHOIR/ Chaelin Kim Seokhyeon Hong Kwan Yun Soojin Choi Inseo Jang Junyong Noh http://arxiv.org/abs/2609.10787v1 2026-09-09T19:49:30Z

Accurate modelling of illumination is central to realistic image synthesis and scene understanding. Yet, there is little exploration into whether image generative models are good at this task or whether physical plausibility remains a key challenge for them. Clearly, significant progress has been made in realistic image synthesis, but do models truly understand lighting in a physically accurate manner? To answer this question, this work proposes a benchmark to assess the lighting understanding and harmonisation capabilities of generative models. Our key insight is that evaluating lighting understanding for such models only requires testing how well they insert novel objects into real photographs whilst maintaining consistent illumination. To do so, we use a multi-illumination dataset with images containing simple objects serving as ``light probes'', and prompt models to inpaint the same object onto the original image, then compare the generated results against the ground-truth light probes. We then estimate the lighting direction, colour and radiance distribution from the inpainted probes, providing a quantitative measure of illumination accuracy and photometric realism. Our work establishes a scalable evaluation protocol to systematically assess how well generative models capture and reproduce real-world lighting, offering a foundation for benchmarking the photometric accuracy of any future models. All code and data are available at https://lvsn.github.io/SheddingLight/ .

2026-09-09T19:49:30Z Accepted to ACM Transactions on Graphics (SIGGRAPH Asia 2026), vol. 45, no. 6, article 227, December 2026. 25 pages. Project page: https://lvsn.github.io/SheddingLight/ Justine Giroux Jack Oliver Hilliard Yannick Hold-Geoffroy Javier Vazquez-Corral Jean-François Lalonde 10.1145/3842579 http://arxiv.org/abs/2609.09821v1 2026-09-09T07:23:51Z

Physics-based character control is a long-standing challenge in computer graphics and robotics, requiring policies that satisfy complex dynamics while producing realistic motion. Recent Deep RL approaches, particularly imitation learning methods such as DeepMimic, have had broad impact beyond animation, influencing robotics by enabling agile and expressive behaviors. While these approaches achieve impressive results, they remain computationally inefficient to train in practice. Despite GPU-accelerated simulation, we find that end-to-end pipelines often underutilize hardware due to overheads outside the physics solver, caused by fragmented GPU kernels and CPU memory access in the critical path. We present InstantMimic, a system that addresses these inefficiencies by making the entire training loop GPU-native. Built on a GPU-native physics backend, our unified pipeline integrates simulation, environment computation, policy inference, and policy updates within a single execution flow. As a result, InstantMimic reduces training time for diverse physics-based skills to a few seconds and makes LLM-agent-driven hyperparameter search practical.

2026-09-09T07:23:51Z Accepted to SIGGRAPH Asia 2026 Conference Papers. 11 pages, 11 figures. Project page: https://scripter36.github.io/projects/instantmimic/ Ikjun Choi Geonho Leem Jungdam Won http://arxiv.org/abs/2609.08084v1 2026-09-08T00:52:01Z

Monocular depth estimation is a ubiquitous yet highly ill-posed computer vision task, with downstream applications in scene reconstruction, computational photography, and robotics, among others. Despite the field's maturity, recent models still struggle to generalize to out-of-distribution inputs and to produce sharp and detailed depth maps. In this paper, we revisit Marigold, a set of techniques for repurposing modern image generation and editing models, powered by the diffusion transformer (DiT) architecture, into state-of-the-art monocular depth estimators. Our recipes target single-step inference from pretrained multi-step flow-matching models, with quantization where needed, preserving model capacity while remaining cheap to run. We analyze the artifacts of naive training and identify two effective remedies: aligning the model's internal representations with semantic features extracted from ground-truth, and adopting a 2-stage fine-tuning protocol built around a novel Sinkhorn-based loss. The results are crisper, cleaner depth maps that generalize well out-of-distribution, with 16-26% improvement in AbsRel over the previous best on KITTI and ETH3D. Qualitatively, our model resolves fur, foliage, and hair-thin edges that have eluded prior models. Furthermore, Marigold V2 achieves state-of-the-art results when applied to other dense regression tasks, such as surface normals estimation and intrinsic image decomposition. Project website: https://hf.co/spaces/huawei-bayerlab/marigold-v2-web

2026-09-08T00:52:01Z SIGGRAPH Asia 2026 Igor Pavlovic Thiemo Wandel Anton Obukhov Luca Bartolomei Andrey Davydov Fabio Tosi Matteo Poggi Sabine Süsstrunk Dengxin Dai http://arxiv.org/abs/2609.07414v1 2026-09-07T12:25:58Z

Image relighting is traditionally tackled via complex inverse rendering pipelines, which suffer from ill-posed optimization, or single-image generative models that ignore crucial multi-view cues necessary for understanding 3D geometry and material interactions. To address these limitations, we introduce a feed-forward generative Transformer for direct single- and multi-view image relighting that entirely bypasses explicit intrinsic property estimation. Adapted from a video foundation model, our architecture features a latent illumination module that dynamically injects target environment maps into spatial features via cross-attention. Furthermore, we employ permutation-invariant positional encodings to symmetrically process unordered multi-view inputs without sequential bias. To train this robust data-driven model, we construct the massive Laval Objaverse Dataset (LOD), comprising 90K objects and 39K unique illuminations. Extensive experiments demonstrate state-of-the-art visual quality, photorealistic relighting quality, and strong zero-shot generalization across single-view, multi-view, and novel-view relighting tasks.

2026-09-07T12:25:58Z SIGGRAPH Asia 2026. Hejun and Jinxi are co-first authors. Code and data are available at: https://github.com/vLAR-group/RelightFormer Hejun Wang Jinxi Li Junwei Jiang Shiwei Mao Hu Cheng Shouwang Huang Bo Yang http://arxiv.org/abs/2609.06723v1 2026-09-06T16:55:21Z

Meshes remain the most practical representation for geometry reasoning and integration into graphics pipelines, yet existing reconstruction methods struggle to produce high-quality meshes. Most state-of-the-art approaches initially learn an intermediate representation (NeRF/3DGS) and treat mesh extraction as a post-processing step, which often leads to oversmoothed surfaces or poor quality meshes with excessive triangle counts.Existing mesh-native optimization methods alleviate some of these issues but suffer from fixed-resolution discretizations and unstable optimization behavior. In this paper, we introduce an adaptive mesh-based optimization framework and a practical mesh rendering technique to address these challenges. Our representation combines an optimizable Delaunay-triangulated tetrahedral grid with a multi-resolution hash grid. The former is refined through point pruning and insertion, while the latter provides latent features for SDF/appearance value predictions. We use volumetric rendering to bootstrap a coarse geometry while leveraging mesh-based rendering for recovering fine-grained details. Additionally, we propose a differentiable, rasterization-based depth-offset rendering formulation, reducing geometric artifacts and improving reconstruction quality. Our method significantly outperforms existing mesh optimization approaches across a variety of object-centric benchmarks while being competitive with state-of-the-art NeRF/3DGS methods.

2026-09-06T16:55:21Z Accepted to SIGGRAPH Asia 2026 Conference Papers | Project page: https://johannes-weidenfeller.github.io/adele | Code: https://github.com/johannes-weidenfeller/adele Johannes Weidenfeller Shaofei Wang Philipp Fürnstahl Siyu Tang 10.1145/3829340.3842214 http://arxiv.org/abs/2609.06591v1 2026-09-06T13:16:48Z

Developing unified physics-based humanoid controllers that can navigate complex 3D scenes and manipulate objects remains a longstanding challenge. Existing approaches are often specialized for either locomotion or object-centric manipulation, or rely on task-specific reward engineering that does not scale well across diverse behaviors. We present CHIP, a unified, physics-grounded framework for learning reusable humanoid interaction skills from heterogeneous motion data. Central to our approach is a conditional interaction prior that models a context-dependent distribution over these skills within a shared discrete space. Our method is trained in three stages. We first learn physics-based motion-imitation policies that acquire grounded teacher behaviors from heterogeneous interaction data. We then distill these behaviors into a context-conditioned interaction prior that captures reusable motion structure across locomotion and manipulation. Finally, we initialize downstream task policies from the pretrained prior and adapt them through prior-regularized online RL post-training. Experiments on a diverse suite of humanoid interaction tasks show that our approach supports scene-aware locomotion, contact-rich object manipulation, and compositional behaviors such as environment-aware object transport and long-horizon skill sequencing, while producing smooth transitions and physically plausible motion.

2026-09-06T13:16:48Z Accepted at SIGGRAPH Asia 2026. Project page: https://jiann-li.github.io/chip-project/ Jianan Li Xiao Chen Tien-Tsin Wong http://arxiv.org/abs/2609.06517v1 2026-09-06T10:18:17Z

Motion retargeting aims to transfer a source motion to target characters with different skeletal structures, proportions, and body shapes. Although recent neural retargeting methods have improved flexibility across diverse skeletons, target-side geometric artifacts such as self-penetration remain difficult to resolve. Specifically, existing geometry-aware approaches often rely on fixed skeleton templates or implicit geometry-conditioned prediction, requiring a single network to account for target geometry deformation, detect target-side artifacts, and predict the corresponding correction from target geometry alone, which limits their ability to generalize across diverse skeleton structures and body shapes. In this paper, we present a geometry-aware motion retargeting framework that explicitly connects artifacts observed in the posed character geometry to motion refinement while preserving the flexibility of skeleton-agnostic neural retargeting. Our method first learns a motion embedding shared across different skeletons using a transformer-based retargeting autoencoder that transfers motion across arbitrary source--target skeleton pairs. Building on this kinematic motion prior, we introduce an artifact-driven refinement module that observes self-penetration on the posed target mesh and converts it into a corrective cue through a motion-to-vertex Jacobian. We further condition motion decoding on target geometry using skinning weight-based joint-aligned geometry features derived from the rest pose mesh. This design combines explicit target-side artifact reasoning with flexible geometry-aware decoding in a unified framework. Experiments on both fixed and arbitrary skeleton structure settings show that our method improves kinematic retargeting accuracy and reduces geometric artifacts, producing plausible motions across seen and unseen target characters.

2026-09-06T10:18:17Z Accepted SIGGRAPH Asia 2026 (Journal Track); Project page https://seokhyeonhong.github.io/projects/kinematic-refinement/ Seokhyeon Hong Chaelin Kim Inseo Jang Soojin Choi Junyong Noh http://arxiv.org/abs/2609.05415v1 2026-09-04T17:59:00Z

Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Existing learned animators are topology-constrained: they rely on category-specific templates or require per-skeleton fine-tuning and reference motions at inference. We present UniMate, a unified foundation model that synthesizes articulated motion for arbitrary skeletons from a rigged 3D asset and a text prompt, with no test-time optimization or per-skeleton retraining. UniMate introduces a topology-aware diffusion transformer, which integrates skeletal topology into attention via three mechanisms: (1) a graph-aware attention bias from pairwise joint relations and geodesic distances; (2) a spectral rotary position embedding generalizing RoPE to arbitrary kinematic trees via the graph Laplacian; and (3) a global topological conditioner attention-pooled from the rest-pose skeleton. We also curate UniML3D, 13,006 motion sequences spanning bipedal, quadrupedal, avian, marine, insectoid, serpentine, and articulated rigid objects with unified canonicalization and text pairing. Trained on this dataset, UniMate outperforms state-of-the-art baselines in quality, generalization, and efficiency, and supports zero-shot cross-topology transfer, in-betweening, expansion, and text-guided editing. Our project page is available at https://linzhanmou.com/unimate/.

2026-09-04T17:59:00Z SIGGRAPH Asia 2026. Project page: https://linzhanmou.com/unimate/ Linzhan Mou Jiahui Lei Zhiyang Dou Chenyue Cai Chaoyue Song Adam Finkelstein Szymon Rusinkiewicz http://arxiv.org/abs/2609.04751v1 2026-09-04T05:31:09Z

3D surface cutting and UV unwrapping are fundamental problems in computer graphics. Traditional geometric optimization methods mainly focus on reducing parameterization distortion, but they often overlook visual semantic coherence in seam layouts. Recent autoregressive generative methods improve semantic coherence, yet limited perception of mesh topology often causes inaccurate local cuts. To address these limitations, we introduce SeamFlow, a novel generative framework for 3D surface cutting. We reformulate the discrete mesh-cutting problem as continuous flow matching in a high-dimensional edge-probability space. Through continuous relaxation, SeamFlow learns a deterministic mapping from a Gaussian prior to a target seam-probability distribution. An evolution network couples local topological tokens with global shape priors and guides smooth probability flow through Ordinary Differential Equation solving. Compared with existing autoregressive generative frameworks, SeamFlow improves topology awareness through edge tokenization while eliminating both 3D spatial projection errors and artificial sequential-order bias. Extensive experiments demonstrate that SeamFlow achieves exceptional semantic coherence and remarkably low parameterization distortion. The project page is https://meshy-dev.github.io/seamflow.

2026-09-04T05:31:09Z Accepted by Siggraph Asia 2026 Yuming Zhao Zangyueyang Xian Qijian Zhang Rendong Liang Qin Jia Ying He Junhui Hou http://arxiv.org/abs/2609.00625v1 2026-09-01T03:05:52Z

Faithfully capturing diverse real-world objects with fuzzy, anisotropic structures, such as hair, fur, fibers, and textiles, for efficient real-time visualization remains challenging. Recent radiance field reconstruction methods capture these structures from multi-view images using translucent volumetric primitives such as 3D Gaussians rather than opaque low-dimensional primitives (e.g., triangles, line segments, and polylines), thereby limiting compatibility with standard depth-tested rasterization, reflection modeling, and physical simulation. We present an inverse rendering method for reconstructing fuzzy geometry using explicit line segments, which are rasterized on a subpixel grid for anti-aliasing to reproduce a semi-transparent appearance. While straightforward to render, optimizing numerous line primitives to match target images poses a significant challenge. We address this by introducing a stochastic differentiable rasterizer for line segments that produces informative gradients with respect to vertex positions, attributes, and discrete connectivity. Experiments on synthetic and real-world datasets show that our method outperforms surface-based approaches in capturing fuzzy boundaries and achieves quality comparable to volumetric representations while relying entirely on explicit geometry. The resulting representation integrates seamlessly with standard graphics pipelines, enabling cross-platform rendering, various shading models, and physical simulation.

2026-09-01T03:05:52Z SIGGRAPH Asia 2026. Project page: https://kenji-tojo.github.io/sa26-line-primitives/ Kenji Tojo Ariel Shamir Nobuyuki Umetani Bernd Bickel http://arxiv.org/abs/2609.00377v1 2026-08-31T21:09:22Z

We present FoldingAgent, an agentic framework for inferring explicit parametric folding programs directly from origami demonstration videos. Our framework leverages the reasoning power of a pre-trained Vision-Language Model (VLM) equipped with a suite of specialized tools that enable the agent to simulate geometric transitions, verify physical plausibility, retrieve and compare visual content, and evaluate its own predictions. To translate visual content into folding programs, we define a parametric space that consists of the paper's geometry and a set of parametric folding actions. Unlike models that predict static crease patterns, our agent operates sequentially and possesses the ability to re-plan its actions, effectively mitigating the compounding errors inherent in multi-step folding. Our approach takes a step toward closing the gap between human origami knowledge, which is primarily shared through unstructured visual demonstrations, and computational methods, which typically rely on structured, parametric representations such as a crease pattern or an executable parametric plan. We evaluate our approach on PurelandFold, a newly curated benchmark of diverse Pureland origami videos with ground-truth geometry and action labels. Our results demonstrate that by combining VLM reasoning with a set of specialized tools and physical simulation, we can successfully transform unstructured visual demonstrations into executable, physically plausible folding procedures.

2026-08-31T21:09:22Z Project Page: https://maya-moriya.github.io/origami-page/ Accepted to SIGGRAPH ASIA 2026 Maya Moriya Sigal Raab Yael Vinker Tali Dekel http://arxiv.org/abs/2608.31003v2 2026-09-02T18:37:49Z

In this work, we propose a novel theoretical view of cage-based deformation based on domain-varying Green' s functions and treat this domain as a new control space for the deformation effects. Harmonic Coordinates (HC) and Green Coordinates (GC) are classic methods in cage-based deformation and serve as the theoretical foundation for shape editing in a range of practical deformation tools. Our method revisits these two classical approaches. Specifically, we propose a framework based on Green' s functions across diverse domains (independent of the cage-enclosed domain) to unify these two techniques. To our knowledge, this represents the first such attempt in nearly two decades. Based on this perspective, we propose a novel cage-based deformation technique that introduces a new control space and utilizes domain-varying Green' s functions to yield varying deformation effects. Our method also establishes a continuous transition of effects from HC to GC as the Green' s function domain $Θ$ expands from the cage region $Ω$ to the entire $\mathbb{R}^2$. We call our method Domain-Varying Green Coordinates (DVGC). When $Θ$ is a disk or a rectangle, the Green' s function possesses analytic or semi-analytic expressions, respectively, enabling the DVGC to be computed without finite element discretization. Furthermore, when $Θ$ is a disk, the DVGC admit a closed-form expression for 2D simplicial cages, thereby eliminating the need for numerical integration. Experiments demonstrate that our method provides a novel control space ranging from more consistent with the cage to more shape-preserving, generating diverse deformation effects by varying the Green' s function domains.

2026-08-31T15:54:38Z SIGGRAPH Asia 2026 Conference Paper Dong Xiao Renjie Chen Bailin Deng 10.1145/3829340.3842236 http://arxiv.org/abs/2608.29322v1 2026-08-29T15:08:31Z

Recent video diffusion models have achieved remarkable generation quality, but high-fidelity results still largely depend on closed-source systems or costly large-scale infrastructure. Test-time scaling (TTS) offers a training-free way to improve lightweight generators by spending additional inference compute, yet existing methods mostly remain within a noise-search paradigm: they sample, select, or perturb denoising trajectories and discard low-scoring candidates after expensive generation. This generate-and-discard process wastes not only computation but also the partial motion, layout, or appearance structure already encoded in recoverable samples. We present \textbf{GEARS} (\textbf{G}uided \textbf{E}diting for \textbf{A}daptive \textbf{R}ecycling \textbf{S}earch), a training-free framework that introduces {diagnosis-guided candidate recycling} into video TTS by turning such candidates into editable priors through a generation-evaluation-editing loop. GEARS consists of two collaborative components. The \textbf{Stage-Aware Scheduler} determines what to repair, when to repair it, and which candidates should be preserved, recycled, or discarded. The \textbf{Candidate Recycler} diagnoses recoverable failures from keyframes and multi-dimensional reward feedback, derives candidate-specific repair prompts, and repairs the corresponding candidates through manifold-aware latent SDEdit. The repaired candidates are recycled into the search pool, creating refinement paths beyond standard noise perturbation while preserving useful structure. Under matched NFE budgets, GEARS consistently outperforms existing video TTS methods on VBench, bringing a 1.3B model to a total score comparable to a 14B counterpart, and ablations verify the necessity of adaptive scheduling, diagnosis-conditioned editing, and manifold-aware re-denoising. Code is available on GitHub.

2026-08-29T15:08:31Z Accepted by ACM TOG (SIGGRAPH Asia 2026) Hangzhou He Lunhao Duan Shanshan Zhao Kaiwen Li Qing-Guo Chen Weihua Luo Yanye Lu 10.1145/3842526 http://arxiv.org/abs/2609.04249v1 2026-08-28T18:10:18Z

Existing audio-video generation methods produce well-synchronized clips but are limited to short durations, while long-video generation methods extend duration through chunk-based iterative synthesis yet lack audio entirely. Generating long audio-video jointly is fundamentally harder than either task alone: each chunk must simultaneously maintain video temporal coherence, audio temporal coherence, and cross-modal synchronization, whose conditioning signals enter the model through different pathways. In this work, we present Encore for long-form synchronized audio-video generation. Our key insight is to factor this challenge into: (1) local continuity handled by iterative generation with explicit cross-chunk context propagation, and (2) global consistency enforced via reference audio-video signals with shifted position embedding. Building on this design, we propose Adaptive Signal Routing (ASR), which introduces learnable attention biases within self-attention and learnable residual scales on cross-attention outputs, enabling the model to adaptively modulate the influence of each conditioning signal. Trained end-to-end for joint audio-video generation, Encore also supports infinite-length audio-to-video and video-to-audio synthesis at inference by conditioning on the ground-truth modality throughout the denoising process. Experiments on our extended VerseBench for long audio-video evaluation demonstrate that Encore significantly outperforms existing methods in both generation quality and temporal coherence. Code and data for this paper are at https://github.com/shaohua-pan/Encore.

2026-08-28T18:10:18Z Accepted by SIGGRAPH ASIA 2026 Shaohua Pan Junbao Chen Shengyi He Jingfeng Xue Wen Tao Haocheng Feng Siming Fan Dongwei Pan Yi Yang Wei He Hang Zhou http://arxiv.org/abs/2608.25203v1 2026-08-25T22:43:39Z

Simulating large-scale free-surface water by coupling a localized 3D fluid solver to a cheaper 2D surface model has long faced a mismatch in wave dynamics: efficient 2D wave models used in graphics are typically either linear or non-dispersive. These models are fast, simple, and accurate for calm, small-amplitude seas, but coupling them with strongly nonlinear 3D solvers produces visible reflections and artifacts at the 2D--3D interface. We address this problem by introducing a nonlinear and dispersive 2D wave model based on the canonical Zakharov formulation. Its Hamiltonian structure, in which the surface elevation and surface potential form a canonical pair ($η$, $ψ$) governed by the wave energy, enables a canonically consistent two-way coupling scheme, allowing information to pass smoothly across the 2D--3D interface. Our 2D solver reduces mean wave-height error by 1.7--5$\times$ over SWE, BEM, and Airy baselines while running more than $10^3\times$ faster than BEM; it achieves greater nonlinear accuracy and coupling fidelity than SWE and Airy, with minor losses in speed and stability. Coupling it with a 3D Navier--Stokes solver yields a full system that suppresses visible seam artifacts across a range of experiments, including dispersion-matching and Kelvin-wake tests, and runs over 4$\times$ faster than a pure GPU NB-FLIP simulation on the same domain.

2026-08-25T22:43:39Z To appear in ACM Transactions on Graphics (SIGGRAPH Asia 2026) Sinan Wang Ruicheng Wang Taiyuan Zhang Fan Feng Jinjin He Yuchen Sun Zhiqi Li Bo Zhu 10.1145/3842540 http://arxiv.org/abs/2608.22821v2 2026-08-25T05:23:29Z

We present SiZeUp, a fast and scalable approach for constructing large-scale 3D urban proxy models directly from calibrated oblique aerial imagery. Our method adopts a height-from-footprint representation, reducing 3D building abstraction to a low-dimensional optimization problem in which building footprints are extruded by a single height parameter. To enable efficient and robust height estimation, we introduce an ordinal depth consistency loss that enforces agreement between the relative depth ordering of rendered proxies and depth priors predicted by a monocular depth model. This is realized through a differentiable renderer that maps parametric building proxies into multi-view depth images, allowing gradients to be propagated from depth supervision to building heights. Our ordinal formulation produces stable optimization in practice and avoids explicit feature matching or dense point cloud reconstruction. Rather than relying on metric depth, which can be unreliable under monocular scale ambiguity, our ordinal depth consistency loss operates on relative depths, providing a more reliable signal across views. Combined with an efficient dynamic view selection, our approach achieves a 23-52$\times$ speedup over state-of-the-art proxy reconstruction pipelines while maintaining comparable proxy-level coverage and volume consistency, making it well suited for large-scale urban modeling tasks.

2026-08-24T05:37:34Z SiZeUp (SZU) accepted to SIGGRAPH Asia 2026 Wenjun Zhou Yunshan Li Qiaoyu Zhu Weidan Xiong Hao Zhang Daniel Cohen-Or Hui Huang http://arxiv.org/abs/2608.21659v2 2026-08-30T04:30:23Z

Vector sketches remain one of the most concise and immediate mediums for abstract human expression. However, generating high-quality vector strokes that exhibit human-like drawing styles remains an open challenge due to the severe scarcity of fine-grained, high-quality text-to-sketch paired data. Existing text-conditioned generation methods often rely on unstable, time-consuming optimization or struggle to generalize to unseen categories in a zero-shot manner. To address these limitations, we present SketchFlow, a novel generative framework rooted in Optimal Transport (OT) theory and flow matching. By leveraging pre-trained CLIP models to bypass labor-intensive image-level text annotations, we formulate cross-modal alignment as a continuous mapping problem directly within the CLIP latent space. To bridge the inevitable modality gap between discrete text concepts and continuous sketch features, we first inject noise into discrete category embeddings to construct a continuous Gaussian Mixture Model (GMM) prior. We then utilize an Optimal Transport Conditional Flow Matching (OT-CFM) model to learn a deterministic vector field mapping from this continuous GMM prior to the target sketch feature distribution. Finally, a Hybrid Diffusion Decoder, fusing 1D U-Net and Transformer architectures, is designed to decode these features into fast and high-fidelity stroke trajectories. Extensive experiments demonstrate that SketchFlow substantially outperforms existing baselines in visual quality and adherence to natural human drawing styles. Furthermore, our geometry-preserving framework demonstrates promising local zero-shot synthesis for prompts beyond the QuickDraw training vocabulary, including unseen concept labels and semantic modifiers, while enabling smooth, continuous semantic interpolation between distinct concepts. Source code is available at: https://github.com/doudin404/SketchFlow.

2026-08-21T22:02:23Z Accepted to SIGGRAPH Asia 2026 Conference Papers. 16 pages Jin Zhou Hongliang Yang Pengfei Xu Hui Huang 10.1145/3829340.3842307 http://arxiv.org/abs/2608.14403v1 2026-08-14T15:44:07Z

Subject-driven image personalization---generating new images that preserve the identity of one or several reference subjects in novel scenes---is a foundational capability for modern visual content creation. It is currently dominated by generalized methods that fine-tune a pretrained multimodal diffusion transformer (MMDiT) on hundreds of thousands to millions of paired \emph{(reference, composed-target)} examples, where each composed target is a synthesized image of the subject in a novel scene. Producing such targets demands a costly multi-stage curation pipeline---LLM-based prompt generation, T2I-based composed-target synthesis, reference-subject extraction, VLM-based quality filtering, and correspondence labeling---and tightly couples each method to a particular target synthesizer and curation choice. We introduce \emph{CRAFT} (Constrained Reward via Attention Fine-Tuning), a single-step ReFL framework that fine-tunes a pre-trained \emph{reference-aware} MMDiT via LoRA adapters using a compact reference-only data construction---$10$K reference images and subject masks, with no composed-target supervision. CRAFT realizes a \emph{Where to look} principle: attention-level rewards align noise- and phrase-token attention with the correct reference subject, and the resulting per-subject attention masks gate a pixel-level identity reward to keep image-space supervision consistent with the learned attention routing. Applied to FLUX.2-klein-9B, CRAFT achieves state-of-the-art performance on XVerseBench \rev{while using no composed-target supervision---only $10$K reference-only samples, whereas prior generalized methods require $150$K to over $2$M composed-target pairs}. The same recipe transfers to other reference-aware backbones, consistently improving performance. Project page: https://jihun999.github.io/projects/CRAFT/.

2026-08-14T15:44:07Z 20 pages, 8 figures, ACM SIGGRAPH Asia 2026 Jihun Park Kyoungmin Lee Jongmin Gim Hyeonseo Jo Jaeyeul Kim Han Zou Zhenpeng Zhan Yan Zhang Sunghoon Im http://arxiv.org/abs/2608.06722v3 2026-09-04T01:04:17Z

With the rise of AI-generated content (AIGC) and advanced techniques for 3D human representation, the task of generating 3D dance movements has become an exciting area of research. Despite significant advancements, current methods often fail to provide comprehensive and distinct control over various multimodal inputs from users, such as music or specific descriptions of desired movements. As a result, the generated motions may be statistically plausible and technically correct, but they often lack depth, expressiveness, and alignment with the user's creative vision. To address this issue, we present CustomDance, a coarse-to-fine interactive system designed for customized 3D dance generation. Inspired by the workflows of expert choreographers, CustomDance introduces a novel paradigm to AI-assisted choreography through three interconnected stages. First, a multimodal Large Language Model (MLLM) analyzes the music and a high-level text prompt to identify key temporal anchors and creative cues for the piece. Next, for each anchor, a multimodal retriever suggests high-quality motion clips from a dance library based on local music and text, empowering the user with concrete and predictable options. Finally, a custom music-conditioned diffusion in-painter seamlessly connects the selected phrases, allowing for iterative, user-guided refinement of the final composition, supported by visualizations of motion dynamics. Our evaluations demonstrate that CustomDance not only highlights the significant creative utility and empowering potential of our AI-assisted choreography paradigm, but also outperforms competitive baselines across quantitative and qualitative comparisons. Project page: https://github.com/XulongT/CustomDance

2026-08-07T02:32:11Z Accepted to SIGGRAPH Asia 2026 Xulong Tang Kaixing Yang Xiaohu Guo Balakrishnan Prabhakaran Rawan Alghofaili http://arxiv.org/abs/2608.02437v2 2026-08-04T03:15:02Z

Single-image feed-forward 3D Gaussian Splatting (3DGS) aims to directly generate a renderable 3D scene representation from one input image, avoiding the cost of multi-view capture and per-scene optimization. However, existing methods are often constrained by a pixel-aligned representation, where Gaussians are predicted from fixed image-grid locations. Such pixel-aligned primitives can produce promising nearby-view renderings, but they remain weakly coupled to underlying scene surfaces and struggle to preserve coherent structures under large viewpoint shifts. We present InfiniSplat, a feed-forward single-image 3DGS framework that moves from a pixel-aligned representation toward a surface-aligned representation. InfiniSplat constructs this representation by first using geometry-guided sampling to place 2D supports according to depth-induced local surface structure, and then applying a query-conditioned implicit decoder to predict Gaussian attributes from the image features queried at these supports. By grounding support locations in geometry while decoupling Gaussian prediction from fixed pixel centers, InfiniSplat produces Gaussian layouts that better follow scene surfaces and reduce scattered primitives caused by grid discretization. Across multiple cross-dataset NVS evaluations, InfiniSplat achieves state-of-the-art performance compared with single-image feed-forward baselines, and demonstrates zero-shot generalization from Hypersim indoor synthetic training to complex open-world scenes. Project page: https://zju3dv.github.io/InfiniSplat.

2026-08-03T16:17:39Z Accepted to SIGGRAPH Asia 2026 (Journal Track). Code: https://github.com/zju3dv/InfiniSplat Jiawei Wang Hao Yu Yongzhen Hu Xinyi Yang Tao Ni Xin Zhan Junbo Chen Xiaowei Zhou Ruizhen Hu Sida Peng http://arxiv.org/abs/2607.24560v1 2026-07-27T15:31:23Z

We introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams, obtained by fine-tuning a pretrained V2V diffusion transformer on event-conditioned data built primarily from Ego4D. Given a monocular video and an event-triggered prompt of the form "when X happens, do Y," EgoPlay infers whether and when event X occurs, preserves pre-event frames, and applies edit Y only to the post-event continuation. Rather than cascading a separate event detector with an editor, EgoPlay learns event recognition, temporal restraint, and pixel-level editing jointly in a single end-to-end model, while also handling negative and multi-event prompts. To support this, we construct a large-scale dataset of 106K event-triggered clip-prompt pairs spanning positive triggers, fabricated-trigger negatives, and multi-event prompts. We then train a bidirectional video diffusion editor with event-triggered supervision and derive a causal variant for chunk-by-chunk streamable inference. We further introduce an event-aware evaluation protocol that separately measures post-trigger editing quality, pre-trigger preservation, and false-trigger robustness. On the Ego4D benchmark, EgoPlay substantially outperforms EgoEdit, the state-of-the-art instruction-based egocentric video editing baseline, with relative gains of 17.7%, 16.9%, and 16.4% in editing quality, visual quality, and background consistency. It also surpasses a VLM-guided detector-editor baseline by 15.7%, 14.5%, and 13.5% on the same metrics, while using less than half the GPU memory.

2026-07-27T15:31:23Z Accepted to SIGGRAPH Asia 2026 as a Conference Paper. Project page: https://egoplay2026.github.io/egoplay Jinjie Mai Gordon Guocheng Qian Willi Menapace Arpit Sahni Chaoyang Wang Ashkan Mirzaei Runjia Li Sergey Tulyakov Bernard Ghanem Peter Wonka Rameen Abdal http://arxiv.org/abs/2607.22830v2 2026-08-19T19:08:30Z

In visual storytelling, human performances are central to creative intent and narrative meaning. However, preserving human identity and performance while enabling flexible visual edits remains challenging for generative video models. We formalize this challenge as identity-preserving video restylization, which propagates scene, lighting, and style changes specified by an edited keyframe across a source video, while preserving facial likeness and performance, including expressions, eye gaze, and lip synchronization. A key obstacle is the absence of paired training data, as identity-preserving restylized video pairs are rare in real-world settings. To address this, we propose a decoupling of source-grounded identity preservation and edit-driven video synthesis. Our key insight is that facial appearance and expression should remain invariant, with illumination being the primary permissible variation. We therefore cast identity preservation as a video relighting problem, while modeling visual edit propagation as controlled video synthesis guided by the edited keyframe. Building on this formulation, we introduce ID-V2V, a video-to-video generative framework integrating complementary control signals: relit facial regions and facial normal maps tightly constrain facial likeness and performance, while edited keyframes and depth sequences enable flexible and temporally coherent generation. This design enables constructing training pairs from a single video, eliminating the need for scarce paired data. Extensive experiments demonstrate that ID-V2V significantly outperforms existing methods in preserving facial likeness and fine-grained facial performance, supports both single- and multi-subject scenarios, and delivers high visual quality, highlighting its potential as a human-centric tool for real-world content production. The code is available at: https://github.com/Eyeline-Labs/ID-V2V.

2026-07-24T18:12:58Z Accepted to SIGGRAPH Asia 2026 Yuancheng Xu Mingming He Pablo Salamanca Li Ma Yash Kant Emmett Steven Paul Debevec Ning Yu http://arxiv.org/abs/2606.23835v3 2026-09-10T17:09:47Z

We present ABACUS, a unified vision-language model that jointly addresses object counting, crowd counting, referring-expression counting, and count-faithful image generation within a single 3B-parameter model. ABACUS introduces three contributions: density-aware adaptive zooming paired with an objectness map from multi-head self-attention decomposition to spatially ground count predictions; a boundary-aware count policy trained via GRPO with nested local, boundary, and global rewards to eliminate over- and undercounting at crop boundaries; and a cycle-consistent GRPO strategy in which the frozen understanding branch scores generated candidates on count-deviation and aesthetic quality, closing the understanding-generation synergy gap without any external critic or annotation. ABACUS achieves state-of-the-art results across seven benchmarks spanning object counting (FSC-147, CARPK), crowd counting (ShanghaiTech A/B), referring-expression counting (REC-8K), count-faithful generation (CoCoCount, T2I-CompBench, GenEval), and count reasoning (CountQA), surpassing both task-specific specialists and larger generalist models. Project page is at https://mondalanindya.github.io/pages/ABACUS.

2026-06-22T18:16:31Z ACM Transactions on Graphics/ SIGGRAPH ASIA 2026, webpage: https://mondalanindya.github.io/pages/ABACUS Anindya Mondal Sauradip Nag Anjan Dutta http://arxiv.org/abs/2606.21938v2 2026-09-10T12:24:12Z

Reconstructing articulated objects from sparse images requires recovering complete geometry, movable parts, and motion parameters. Recent methods typically separate geometry reconstruction, part reasoning, and articulation estimation into different stages. This separation can weaken consistency between shape, active parts, and motion, while also incurring substantial inference cost. We introduce Artic-O, an end-to-end, feed-forward framework for articulated object reconstruction via latent geometry learning. Instead of fitting geometry in image or view space, Artic-O maps sparse multi-state observations into a pretrained latent geometry space, where a frozen flow-matching decoder provides a complete-shape prior for recovering visible and occluded structures. To connect geometry with articulation, Artic-O fuses visual tokens, geometry latents, and point-wise decoder features in an image-grounded part-reasoning module for active-part segmentation and articulation prediction. We further train the model with a geometry-to-articulation curriculum and a decoupled two-pass strategy to balance reconstruction and part-level supervision. On PartNet-Mobility, Artic-O achieves strong reconstruction quality while being substantially more efficient than LARM, a strong prior method. It reduces Chamfer Distance, improves F-score, and achieves comparable or better articulation accuracy across most joint metrics, while reducing inference time from 9 minutes to about 0.3 seconds per object.

2026-06-20T08:15:30Z Accepted to SIGGRAPH Asia 2026 Conference Papers. Project page/code: https://github.com/Wxyxixixi/Artic-O Xuyang Wang Zhenyu Li Jian Ding Habib Slim Peter Wonka Hongdong Li Mohamed Elhoseiny http://arxiv.org/abs/2605.30338v2 2026-08-18T20:12:12Z

Reconstructing physically stable 3D scenes from a single RGB image enables casual images to be converted into simulation-ready digital assets for applications such as immersive interaction and content creation. However, existing single-image reconstruction methods fall short in capturing the physical structure of a scene. As a result, they often produce geometrically plausible but physically inconsistent results, including object floating and penetration, which lead to unstable behavior in physics simulations. Image-conditioned scene generation methods improve physical plausibility but often rely on strong scene priors, yielding plausible yet inaccurate object arrangements that fail to match the input image. We propose REST3D, a single-image reconstruction framework that can reconstruct physically stable 3D scenes by integrating physical scene understanding with physics-constrained refinement. We first introduce an agentic physical scene understanding technique that constructs a scene-tree representation capturing object physical states and inter-object relationships from a gravity-support perspective, providing a structural prior for reconstruction. Leveraging this structure, we initialize the scene using image-to-3D models, followed by scene-tree-guided alignment and physics-constrained optimization to resolve physical violations while preserving visual consistency with the input image. Experiments show that our method significantly reduces physical errors and improves simulation stability on both synthetic and real-world datasets while maintaining strong reconstruction quality. We further demonstrate the reconstructed scenes in VR-based human-object interaction, showing their potential for immersive applications.

2026-05-28T17:59:01Z SIGGRAPH Asia 2026, Project page: https://shirleymaxx.github.io/REST3D/ Xiaoxuan Ma Jiashun Wang Nicolas Ugrinovic Yehonathan Litman Kris Kitani http://arxiv.org/abs/2605.17557v3 2026-08-31T17:25:49Z

We propose a lightweight real-time method for reconstructing strand-based hair G-Buffers from severely undersampled rasterized inputs. Our pipeline first applies neural spatial reconstruction and temporal accumulation to recover hair coverage, i.e., fractional hair visibility within a pixel, and tangent. It then uses a tangent-guided reconstruction step to complete the position, which is subsequently used for physically based deferred hair shading. We evaluate our method across a diverse set of hairstyles, including straight, wavy, afro, and ponytail styles, under both static and dynamic scenarios. Our method achieves higher hair reconstruction quality than general industrial neural reconstruction solutions such as DLSS and FSR.

2026-05-17T17:37:57Z ACM SIGGRAPH ASIA 2026 Conference Paper Chenghao Wu Yuefan Shen Tao Huang Kai Yan Zahra Montazeri Kui Wu http://arxiv.org/abs/2605.14703v2 2026-09-02T18:23:41Z

The high dynamic range (HDR) video ecosystem is approaching maturity, but the problem of upconverting legacy standard dynamic range (SDR) videos persists without a convincing solution. We propose a framework for HDR video synthesis from casual SDR footage by leveraging large-scale generative video models. We introduce a Multi-Exposure Video Model (MEVM) that can predict exposure-bracketed linear SDR video sequences from a single nonlinear SDR video input. We further propose a learnable Video Merging Model (VMM) that merges the predicted exposure-bracketed video into a high-quality HDR sequence while preserving detail in both shadows and highlights. Extensive experiments, quantitative and qualitative evaluation, and a user study demonstrate that our approach enables robust HDR conversion for in-the-wild examples from casual consumer videos and even iconic films. Finally, our model can support HDR synthesis pipelines built upon existing SDR generative video models. Output HDR videos can be viewed on our supplementary webpage: sdr2hdrvideo.github.io

2026-05-14T11:21:10Z SIGGRAPH Asia 2026, Webpage is https://sdr2hdrvideo.github.io SaiKiran Tedla Francesco Banterle Trevor Canham Karanpreet Raja David B. Lindell Kiriakos N. Kutulakos Jiacheng Li Feiran Li Daisuke Iso http://arxiv.org/abs/2605.13343v3 2026-09-24T17:48:50Z

Interactive simulation solves Ax=b for a sparse SPD A that changes every frame, inside an 8-16 ms budget. At a few thousand unknowns, the setup of algebraic multigrid alone exceeds that budget, while Jacobi and other local preconditioners have no setup but cannot move error across the domain. We learn a preconditioner for this gap: a graph-and-attention network predicts an SPD approximate inverse in H^2-matrix format. On a spatially ordered 3D mesh, blocks of the true inverse lose rank as the clusters they couple move apart; the nested bases of the format follow that decay, so inference and apply are dominated by leaf-block work linear in N, where a dense inverse costs N^2. Our main finding concerns training. Probe losses reach M only through a product with A, so their gradient vanishes on the near-null modes that set the conjugate-gradient iteration count. A truncated Kaporin condition number has no such factor; changing only the objective cuts iterations on a held-out frame from 116 to 33. On a ladder of stiff tetrahedral diffusion problems ours alone fits an 8.3 ms (120 fps) frame from N=572 to 3,647.

2026-05-13T11:02:27Z Accepted to SIGGRAPH Asia 2026 Posters (SA Posters '26). 3 pages; 2-page supplement as ancillary file. Supersedes v1-v2 (Hierarchical Transformer Preconditioning for Interactive Physics Simulation): their cosine-Hutchinson objective carries a factor lambda in its gradient on near-null modes; this version trains a truncated Kaporin condition number and evaluates on 3D tet meshes Carl Osborne Minghao Guo Crystal Owens Wojciech Matusik 10.1145/3829333.3847989 http://arxiv.org/abs/2604.28130v4 2026-09-14T14:55:42Z

Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts joint positions and an analytical inverse-kinematics (IK) stage recovers joint rotations. While effective, this design is inherently limited, since joint positions do not fully determine rotations and leave degrees of freedom such as bone-axis twist ambiguous, and the non-differentiable IK stage prevents the system from adapting to noisy predictions or optimizing for the final animation objective. In this work, we present the first fully end-to-end framework in which both Video-to-Pose and Pose-to-Rotation are learnable and jointly optimized. We observe that the ambiguity in pose-to-rotation mapping arises from missing coordinate system information: the same joint positions can correspond to different rotations under different rest poses and local axis conventions. To resolve this, we introduce a reference pose-rotation pair from the target asset, which, together with the rest pose, not only anchors the mapping but also defines the underlying rotation coordinate system. This formulation turns rotation prediction into a well-constrained conditional problem and enables effective learning. In addition, our model predicts joint positions directly from video without relying on mesh intermediates, improving both robustness and efficiency. Both stages share a skeleton-aware Global-Local Graph-guided Multi-Head Attention (GL-GMHA) module for joint-level local reasoning and global coordination. Experiments on Truebones Zoo and Objaverse show that our method reduces rotation error from ~17 degrees to ~10 degrees, and to 6.54 degrees on unseen skeletons, while achieving ~20x faster inference than mesh-based pipelines. Project page: https://animotionlab.github.io/MoCapAnythingV2/

2026-04-30T17:16:38Z Accepted to ACM Transactions on Graphics (SIGGRAPH Asia 2026). Project page: https://animotionlab.github.io/MoCapAnythingV2/ Kehong Gong Zhengyu Wen Dao Thien Phong Mingxi Xu Weixia He Qi Wang Ning Zhang Zhengyu Li Guanli Hou Dongze Lian Xiaoyu He Mingyuan Zhang Hanwang Zhang http://arxiv.org/abs/2604.08547v2 2026-09-07T09:23:23Z

We propose Skelebones, a Scaffold-Skin Rigging System built on three steps: (1) Bones compress temporally consistent Gaussian or mesh sequences into free-form bones with smooth skinning weights, approximating non-rigid deformations via linear blend skinning (LBS); (2) Skeleton extracts the Mean Curvature Skeleton (MCS) from the canonical shape and temporally refines its topology and kinematics into a compact skeletal structure; and (3) Binding connects the skeleton and bones through non-parametric Partwise Motion Matching (PartMM), which synthesizes novel bone motions by matching, retrieving, and blending existing ones. Together, these steps compress the dynamics of 4D shapes into compact skelebones that are simultaneously controllable and expressive. The resulting representation is category-agnostic, meaning template-free; motion-adaptive, with dynamic topology; and topology-correct, with a skeleton consistent with the surface geometry. PartMM requires no learning. We validate our method on both synthetic and real-world datasets, achieving substantial reanimation improvements on unseen poses: a 17.3 dB PSNR gain over LBS on DNA-Rendering and a 45.6 dB gain over Bag-of-Bones on ActorsHQ, while preserving high rendering fidelity for characters with complex non-rigid dynamics. PartMM generalizes robustly to both Gaussian and mesh representations, excelling in low-data regimes of approximately 1,000 frames, with a 48.4 RMSE improvement over LBS and improvements of more than 20 over GRU- and MLP-based methods. Code will be publicly released at https://cookmaker.cn/gaussianimate/.

2026-04-09T17:59:59Z Accepted by SIGGRAPH Asia 2026, Page: https://cookmaker.cn/gaussianimate Jiaxin Wang Dongxin Lyu Zeyu Cai Zhiyang Dou Cheng Lin Anpei Chen Yuliang Xiu http://arxiv.org/abs/2604.01479v3 2026-08-21T05:25:51Z

Sparse-view 3D modeling represents a fundamental tension between reconstruction fidelity and generative plausibility. While feed-forward reconstruction excels in efficiency and input alignment, it often lacks the global priors needed for structural completeness. Conversely, diffusion-based generation provides rich geometric details but struggles with multi-view consistency. We present RecGen3D, a framework that combines these two paradigms into a cooperative system. To overcome inherent conflicts in coordinate spaces, 3D representations, and training objectives, we align both models within a shared canonical space. We employ decoupled cooperative learning, which maintains stable training while enabling seamless collaboration during inference. Specifically, the reconstruction module is adapted to provide canonical geometric anchors, while the diffusion generator leverages latent-augmented conditioning to refine and complete the geometric structure. Experimental results demonstrate that RecGen3D achieves superior fidelity and robustness, outperforming existing methods in creating complete and consistent 3D models from sparse observations.

2026-04-01T23:35:40Z Accepted to SIGGRAPH Asia 2026 (Conference Papers). 21 pages including supplementary material. Code: https://github.com/zsh523/RecGen3D Zhisheng Huang Jiahao Chen Cheng Lin Chenyu Hu Hanzhuo Huang Zhengming Yu Mengfei Li Yuheng Liu Zekai Gu Zibo Zhao Yuan Liu Xin Li Wenping Wang http://arxiv.org/abs/2603.11421v2 2026-08-24T11:17:13Z

Text-driven video generation has democratized film creation, but camera control in cinematic multi-shot scenarios remains a significant block. Implicit textual prompts lack precision, while explicit trajectory conditioning imposes prohibitive manual overhead and often triggers execution failures in current models. To overcome this bottleneck, we propose a data-centric paradigm shift, positing that aligned (Caption, Trajectory, Video) triplets form an inherent joint distribution that can connect automated plotting and precise execution. Guided by this insight, we present ShotVerse, a ``Plan-then-Control'' framework that decouples generation into two collaborative agents: a VLM (Vision-Language Model)-based Planner that leverages spatial priors to obtain cinematic, globally aligned trajectories from text, and a Controller that renders these trajectories into multi-shot video content via a camera adapter. Central to our approach is the construction of a data foundation: we design an automated multi-shot camera calibration pipeline aligns disjoint single-shot trajectories into a unified global coordinate system. This facilitates the curation of ShotVerse-Bench, a high-fidelity cinematic dataset with a three-track evaluation protocol that serves as the bedrock for our framework. Extensive experiments demonstrate that ShotVerse effectively bridges the gap between unreliable textual control and labor-intensive manual plotting, achieving superior cinematic aesthetics and generating multi-shot videos that are both camera-accurate and cross-shot consistent.

2026-03-12T01:27:08Z SIGGRAPH Asia 2026 Songlin Yang Zhe Wang Xuyi Yang Songchun Zhang Xianghao Kong Taiyi Wu Xiaotong Zhao Ran Zhang Alan Zhao Anyi Rao http://arxiv.org/abs/2602.18741v3 2026-09-19T09:50:20Z

Spectral rendering reproduces the wavelength-dependent appearance that RGB rendering cannot: metamerism, colour shifts under spectrally rich illumination, coloured glass, metallic reflection and subsurface scattering. It requires a spectrally aware renderer, but the rendering ecosystem is predominantly RGB: game engines, cloud render farms, GPU rasterisers and most offline renderers consume RGB alone, with no access to the internal wavelength propagation that spectral rendering relies on. We introduce learned spectral codes, a compact linear representation that enables general spectral rendering through unmodified RGB pipelines. A trained encoder compresses any visible-range spectral quantity into a small latent vector; the codes are packed as RGB triplets and processed by an off-the-shelf RGB renderer. The codec preserves the arithmetic of light transport, exactly for scaling and addition and approximately for element-wise products, so two standard RGB passes suffice to produce results closely matching a full spectral rendering. The same codec handles reflectance, illumination, coloured glass, conductors, and participating media: one pipeline across material classes, with no per-material modification to the renderer. Where spectral asset data is unavailable, lightweight neural upsamplers bridge legacy RGB inputs to the latent space. Across diverse materials and illumination, the method yields substantial quality improvements on the cases where RGB rendering fails most visibly, at rendering cost comparable to efficient spectral-sampling techniques and with no changes to the renderer.

2026-02-21T07:30:09Z Accepted at SIGGRAPH Asia 2026; to appear in ACM Transactions on Graphics 45(6). v3: accepted manuscript, substantially revised content, revised title. Supplemental material attached as an ancillary file ACM Transactions on Graphics 45, 6, Article 257 (2026) Jiaqi Yu University of York Dar'ya Guarnera University of York Giuseppe Claudio Guarnera University of York Lumirithmic Ltd 10.1145/3842506 http://arxiv.org/abs/2602.14048v2 2026-09-03T04:53:28Z

Real-time embodied social interaction places two equally demanding requirements on an agent: continuously generating fluent multimodal interaction behavior, and proactively reasoning over accumulated dialogue and visual context to decide when to take initiative. These requirements must both be satisfied under a strict latency budget, making them difficult to meet simultaneously. We present ProAct, a dual-system framework that manages these time-critical requirements by integrating a low-latency Behavioral System for streaming multimodal interaction with a slower Cognitive System that performs long-horizon social reasoning and produces high-level proactive intentions. The Cognitive System incorporates an efficient memory mechanism and a user-motivation prediction module to reason over accumulated dialogue and visual context and determine when proactive intervention is appropriate. The Behavioral System further includes an intention-conditioned streaming flow-matching motion generator with a disentangled ControlNet branch, which translates deliberative intentions into continuous non-verbal behavior without disrupting interaction fluency. We deploy ProAct on a physical humanoid robot and validate the framework through comprehensive experiments, including real-world user studies, motion-generation benchmarks, and evaluation on ProActBench, a new, targeted benchmark for evaluating proactive trigger detection and restraint in embodied interaction.

2026-02-15T08:27:34Z SIGGRAPH ASIA 2026 (Journal Track). Project Page: https://proactrobot.github.io/ ACM Transactions on Graphics (TOG) 2026 Zeyi Zhang Zixi Kang Ruijie Zhao Yusen Feng Biao Jiang Hanyu Ji Libin Liu 10.1145/3842576 http://arxiv.org/abs/2602.01335v2 2026-08-27T18:01:52Z

A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric. Despite the remarkable progress of generative AI, existing models remain largely confined to pixel-level instruction alignment and surface-level appearance preservation, failing to capture the underlying abstract logic necessary for genuine metaphorical generation. To bridge this gap, we introduce the task of Visual Metaphor Transfer (VMT), which challenges models to autonomously decouple the "creative essence" from a reference image and re-materialize that abstract logic onto a user-specified target subject. We propose a cognitive-inspired, multi-agent framework that operationalizes Conceptual Blending Theory (CBT) through a novel Schema Grammar ("G"). This structured representation decouples relational invariants from specific visual entities, providing a rigorous foundation for cross-domain logic re-instantiation. Our pipeline executes VMT through a collaborative system of specialized agents: a perception agent that distills the reference into a schema, a transfer agent that maintains generic space invariance to discover apt carriers, a generation agent for high-fidelity synthesis and a hierarchical diagnostic agent that mimics a professional critic, performing closed-loop backtracking to identify and rectify errors across abstract logic, component selection, and prompt encoding. Extensive experiments and human evaluations demonstrate that our method significantly outperforms SOTA baselines in metaphor consistency, analogy appropriateness, and visual creativity, paving the way for automated high-impact creative applications in advertising and media. Project page with source code and self-contained skills is at https://yuci-gpt.github.io/Beyond-Pixels/.

2026-02-01T17:01:36Z Accepted to SIGGRAPH ASIA 2026; Project page: https://yuci-gpt.github.io/Beyond-Pixels/ Yu Xu Yuxin Zhang Lin Gao Oliver Deussen Tong-Yee Lee Fan Tang http://arxiv.org/abs/2512.20386v3 2026-08-31T17:41:22Z

We live in a world filled with anisotropy, a ubiquitous characteristic of both natural and engineered systems. In this study, we concentrate on space deformation and introduce Anisotropic Green Coordinates (AGC), which provide versatile effects for cage-based and variational deformations in both two and three dimensions. The AGC are derived from the anisotropic Laplace equation $\nabla\cdot(\mathbf{A}\nabla u)=0$, where $\mathbf{A}$ is a symmetric positive definite (SPD) matrix. Based on this equation, we establish the boundary integral formulation, which is subsequently discretized to derive the deformation coordinates defined on the vertices and normals of oriented simplicial cages. Our method satisfies basic properties such as linear reproduction and translation invariance, and possesses closed-form expressions for both 2D and 3D scenarios. We also give an intuitive geometric interpretation of the approach, demonstrating that our method can generate a quasi-conformal mapping. We demonstrate both theoretically and empirically that the deformation effect is more pronounced when the normal of the cage face aligns with the eigenvector corresponding to the larger eigenvalue of $\mathbf{A}$. This indicates that anisotropy amplifies the deformation sensitivity along this direction, enabling more targeted cage design and matrix selection. Furthermore, we derive the gradients and Hessians of the deformation coordinates and employ the local-global optimization framework to facilitate variational shape deformation, enabling flexible shape manipulation while achieving as-rigid-as-possible (ARAP) shape deformation. Experimental results demonstrate that AGC offer versatile and diverse deformation options, providing artists with enhanced flexibility and introducing a novel perspective on spatial deformation.

2025-12-23T14:21:24Z Accepted by SIGGRAPH Asia 2026 Journal Track Dong Xiao Renjie Chen Bailin Deng 10.1145/3842502 http://arxiv.org/abs/2512.16767v3 2026-09-02T12:28:33Z

Posing 3D characters is a fundamental task in computer graphics. However, existing paradigms, ranging from traditional auto-rigging to recent pose-conditioned generative models, frequently struggle with inaccurate skinning weights, fixed mesh topologies, and poor pose conformance. These challenges have become particularly pronounced with the recent explosion of AI-generated 3D assets, which often exhibit flawed structures and fused geometry. To address these issues, we introduce \textbf{Make-It-Poseable}, a novel feed-forward framework that reformulates character posing as a skinning-free latent-space transformation problem. By decoupling shape deformation from the constraints of fixed mesh connectivity, our method directly operates on compact latent representations to reconstruct characters in target poses. To achieve this, our framework integrates a latent posing transformer for shape manipulation, a dense pose representation for fine-grained control, and an adaptive completion module optimized via a bipartite-matched latent loss to robustly handle topological changes. Extensive experiments demonstrate that our method significantly outperforms existing baselines in posing quality. Furthermore, our design shows promising generalization to diverse morphologies such as quadrupeds in our qualitative tests, and supports various 3D authoring applications such as part replacement and refinement.

2025-12-18T17:01:44Z Accepted to SIGGRAPH Asia 2026. Project page: https://jasongzy.github.io/Make-It-Poseable/ Zhiyang Guo Ori Zhang Jax Xiang Alan Zhao Zhenxun Yuan Wengang Zhou Houqiang Li http://arxiv.org/abs/2512.11199v2 2026-09-01T07:37:22Z

Computer-aided design (CAD) defines 3D models as compact, precise, and editable representations, making it directly useful for several fields. Recently, CAD generation has been gaining more attention in both the research community and industry. Crafting CAD models has long been a painstaking and time-intensive task, demanding both precision and expertise from designers. Prior works have achieved early success in single-part CAD generation, which is not well-suited for real-world applications, as multiple parts need to be assembled under semantic constraints and geometric compatibility. In this paper, we propose CADKnitter, a compositional CAD generation framework with geometric-guiding cues to steer diffusion sampling. CADKnitter is able to generate a complementary CAD part that follows both the geometric constraints of the given CAD model and the semantic constraints of the desired design text prompt. We also curate a dataset, so-called KnitCAD, containing over 310,000 samples of CAD models, along with textual prompts and assembly metadata that provide semantic and geometric constraints. Intensive experiments demonstrate that our proposed method outperforms other state-of-the-art baselines by a clear margin. Our project page is available at https://cadknitter.github.io/.

2025-12-12T01:06:38Z Accepted to SIGGRAPH Asia 2026 Conference Tri Le Khang Nguyen Baoru Huang Tung D. Ta Anh Nguyen http://arxiv.org/abs/2510.20820v4 2026-09-02T01:38:41Z

Existing personalized image generators still struggle to preserve multiple reference identities in natural and coherent multi-human generations. To address these limitations, we present CanvasComposer, an interactive framework for personalized group photo generation. Inspired by professional image-editing software, CanvasComposer allows users to place reference subjects on a shared canvas, where each subject keeps its own RGBA cutout of the input. This multi-reference canvas preserves reference content under overlap while providing an intuitive interface for organizing multiple identities; the subjects remain separate elements on the input canvas, and the model outputs a single personalized and harmonized image. To keep this representation efficient, transparent latent pruning retains only tokens from each subject's non-transparent region, and cross-reference training mitigates copy-paste artifacts by learning to harmonize references sampled from different images. Extensive experiments demonstrate that CanvasComposer achieves coherent generation and strong identity preservation compared to state-of-the-art methods in multi-human personalized image generation. Project page: https://snap-research.github.io/canvascomposer

2025-10-23T17:59:55Z Accepted to SIGGRAPH Asia 2026 Conference Papers. 16 pages including appendix. Project page: https://snap-research.github.io/canvascomposer Gordon Guocheng Qian Ruihang Zhang Tsai-Shien Chen Yusuf Dalva Anujraaj Argo Goyal Willi Menapace Ivan Skorokhodov Meng Dong Arpit Sahni Daniil Ostashev Ju Hu Mukesh Singhal Sergey Tulyakov Kuan-Chieh Jackson Wang http://arxiv.org/abs/2503.19634v2 2026-08-31T13:03:17Z

Burst image super-resolution (BISR) reconstructs a high-resolution keyframe by aggregating complementary sub-pixel evidence from a short burst of low-resolution frames. Existing methods often process all burst frames with heavy backbones or maintain deep cross-frame interaction throughout the network, leading to redundant computation on non-key frames and limiting scalability with burst length. In this work we propose BurstMamba, a BISR architecture built on a simple principle: allocate most compute to reconstructing the keyframe, and process the burst primarily to extract sub-pixel priors. To this end, BurstMamba decouples BISR into a high-capacity keyframe super-resolution stream and a lightweight burst stream that interacts with it only through stage-wise residual injection. To improve burst-to-keyframe transfer, we introduce Gather -> Aggregate -> Scatter (GAS), which uses correspondence only for cross-frame message passing while preserving native-view features through a residual connection, and a wavelet-conditioned state update that biases selective routing toward high-frequency regions. Across SyntheticSR, RealBSR-RAW, and RealBSR-RGB, BurstMamba achieves state-of-the-art results. Extensive ablations show that the proposed compute separation, GAS, and wavelet-conditioned routing each contribute to the model's accuracy and scaling.

2025-03-25T13:22:55Z Accepted at SIGGRAPH Asia 2026 Ozan Unal Steven Marty Dengxin Dai