https://arxiv.org/api/xFTsnggrwNmxxZxB9pdLDoy2R/Q 2026-09-27T19:38:38Z 200 85 0 http://arxiv.org/abs/2608.30184v1 2026-08-31T03:09:16Z

Volumetric video enables immersive free viewpoint rendering of dynamic real world scenes, yet existing methods struggle with long sequences and complex motions, often leading to temporal instability and visual artifacts. To address these challenges, we propose \ourname, a Gaussian splatting based framework for volumetric video reconstruction. Our key insight is that explicitly tracking long term complex motion with individual Gaussian primitives is inherently unstable. Instead, we organize Gaussians around time conditioned anchors that localize their spatial and temporal support, thereby reducing long range motion complexity. We further introduce a temporal windowing strategy to activate only anchors relevant to the queried time, which improves scalability and temporal coherence. In addition, to ensure spatial and temporal stability, we design a compact set of multi level anchor features that encode global features, local spatial features, and local temporal features, jointly constraining Gaussian generation. Extensive experiments demonstrate that \ourname \ consistently outperforms prior methods on long sequence volumetric videos with complex motions. Project page: https://github.com/WuJH2001/ATGS.

2026-08-31T03:09:16Z ACM ToG(SIGGRAPH'2026) Jiahao Wu Jie Liang Die Hu Jiayu Yang Kaiqiang Xiong Xiang Li Xiaoyun Zheng Chao Wang Ronggang Wang http://arxiv.org/abs/2608.27735v1 2026-08-27T21:51:16Z

We present ABCD (Alpha-Composited Block Coordinate Descent), an out-of-core training framework for alpha-composited radiance fields, instantiated here for 3D Gaussian Splatting. Our method reformulates training as block coordinate descent over spatial partitions: only one block of parameters is active at a time, while all others are frozen. By exploiting the associativity of alpha blending, these inactive regions can be pre-rendered and collapsed into foreground and background RGBA images. As a result, for fixed partition size and image resolution, peak VRAM becomes O(1) with respect to total scene extent, rather than growing with full scene size. This enables GPUs with limited memory to train scenes that would otherwise not fit in core. In experiments, our method closely preserves the reconstruction quality of 3DGS, with less than 5% PSNR degradation, while ABCD with compositing ablated suffers roughly 40% degradation. Our code can be found at https://github.com/shiukaheng/abcd

2026-08-27T21:51:16Z Presented at ACM SIGGRAPH 2026 Posters ACM SIGGRAPH 2026 Posters (SIGGRAPH Posters '26), Article 62, 3 pages, 2026 Ka Heng Shiu Kartic Subr 10.1145/3799825.3818779 http://arxiv.org/abs/2609.05487v1 2026-08-24T21:39:16Z

We present a robotic electrospinning platform and design method for depositing nanofiber membranes onto non-planar, three-dimensional conductive geometries. Conventional electrospinning relies on fixed emitters and planar grounded collectors, which restricts deposition to flat substrates: on concave geometries, field shielding prevents fibers from reaching recessed regions, and material bridges across elevated features instead. We address this with a custom end-effector integrated with a six-axis UR20 arm. The tool carries a localized stepper-driven syringe pump that maintains consistent polymer flow independent of orientation, and routes high-voltage DC (up to 25 kV) directly to a robot-mounted needle, turning the arm into a mobile emitter with full kinematic control over position, orientation, working distance, and traversal velocity. Toolpaths that continuously reorient the emitter along surface normals give access to concave topologies unreachable by fixed-axis systems. We characterize the resulting deposition behavior in two parts. A catalog of four bio-compatible polymer systems (PEO, PVA, keratin-PEO, silk-PEO) establishes the operating envelope, reporting deposition speed, jet stability, fiber size, alignment, and durability for each. A taxonomy of 3D-printed conductive scaffolds spanning geometric primitives, hybrid compositions, and square, triangular, and hexagonal lattices links collector geometry to fiber alignment, density, and cross-void bridging. We also demonstrate programmable grounding, in which selectively energized pins in an array steer deposition without changing physical geometry. Assembly instructions and toolpath-generation code are released as an open-source repository.

2026-08-24T21:39:16Z 15 pages, 10 figures. Published in Proceedings of the ACM on Computer Graphics and Interactive Techniques (SIGGRAPH 2026). Open-source hardware and toolpath code: https://github.com/Critical-Matter-MIT-Media-Lab/Custom-3D-Electrospinning Proc. ACM Comput. Graph. Interact. Tech. 9, 3, Article 43 (July 2026), 16 pages Wai Lok Wan Ayah Mahmoud Sergio Mutis Avantika Velho Annie Xing Behnaz Farahi 10.1145/3816080 http://arxiv.org/abs/2607.11644v1 2026-07-13T14:58:57Z

This work explores the motion transfer from one video to another, which is crucial in animation for diverse characters. Previously, video motion transfer has been largely explored between human and human-like characters, enabling a lot of applications in digital creation. However, these approaches encounter a main limitation. Specifically, related technical pipelines heavily rely on a predefined human skeleton structure and accordingly require skeleton-conditional model training. On the one hand, these methods are difficult to generalize to diverse characters, such as animals from different species, while preserving their unique motion styles. On the other hand, labeled data in diverse skeletons is limited, which additionally restricts the large-scale training for the task. In this paper, we jump out of the skeleton-based motion transfer framework and propose a training-free motion transfer framework, named Motion4Motion. Motion4Motionmodels the motion flow of the character in a video instead of skeletons, which makes motion transfer across species easier. Extensive experimental results and novel applications show our methods outperform baselines impressively. Project page is available at https://lhchen.top/Motion4Motion.

2026-07-13T14:58:57Z SIGGRAPH 2026 Ling-Hao Chen Zixin Yin Duomin Wang Xianfang Zeng Gang Yu http://arxiv.org/abs/2608.13589v1 2026-07-13T03:02:33Z

As human space exploration returns to the Moon, astronauts need rapid access to procedural information during extravehicular activities (EVAs), where attention is divided across navigation, repair tasks, tool handling, and environmental risk. The challenge is not the absence of information, but surfacing the right information at the right moment. We present GAIN-AI (Guided Assistant for Intelligent Navigation), a context-aware AI assistant and minimal heads-up interface for procedural guidance in simulated lunar EVA. The system operates in two layers. The first grounds a large language model with structured context: EVA procedure documents, live telemetry data, and error-handling protocols encoded as JSON. The second restructures that output into three compact units for AR display: Goal, Task, and Verification. Evaluated on 111 synthetic EVA scenarios, the system scores 10.0/10 on nominal conditions and 8.15/10 on single-fault scenarios, with performance degrading on multi-fault and boundary-threshold cases.

2026-07-13T03:02:33Z 4 pages, 4 figures, 1 table. Accepted to ACM SIGGRAPH 2026 Conference Posters, July 19-23, 2026, Los Angeles, California, USA Rodrigo Gallardo Qilmeg Doudatcz Ganit Goldstein Ilkyaz Sarimehmetoglu Sergio Mutis Alexander Htet Kyaw Anita Lin Clara Emmerling Berfin Ataman Skylar Tibbits 10.1145/3799825.3818743 http://arxiv.org/abs/2607.08770v1 2026-07-09T17:59:52Z

Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures, while existing generative models struggle with long-term stability. We propose LongE2V, a novel approach that leverages pre-trained video diffusion priors to jointly handle event-based video reconstruction, prediction, and frame interpolation. By fine-tuning a foundational video model, our approach achieves high data efficiency and superior perceptual quality. We introduce Autoregressive Unrolling and Adaptive Context Switching to mitigate temporal drift in extremely long sequences. We also propose Reencoding Alignment with Cross Residual Correction to ensure precise bidirectional consistency during frame interpolation. Furthermore, Event Voxel Density Augmentation ensures robustness across varying sensor resolutions. Extensive experiments on real-world benchmarks demonstrate that LongE2V outperforms state-of-the-art methods across all three tasks, exhibiting exceptional temporal coherence and zero-shot generalization. Project page: https://cdfan0627.github.io/LongE2V-page/

2026-07-09T17:59:52Z SIGGRAPH 2026. Project page: https://cdfan0627.github.io/LongE2V-page/ Cheng-De Fan Chun-Wei Tuan Mu Chen-Wei Chang Chin-Yang Lin Kun-Ru Wu Yu-Chee Tseng Yu-Lun Liu http://arxiv.org/abs/2607.08741v1 2026-07-09T17:41:49Z

Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics. While recent offline motion generation approaches offer precise control via text and kinematic constraints, they lack the inference speed required for interactive settings. Conversely, existing online methods enable real-time synthesis but often sacrifice controllability or struggle with complex text semantics and long-horizon goals due to limited context windows. In this work, we introduce ARDY, a streaming generation framework that bridges this gap by enabling high-fidelity motion generation controllable via online text prompts and flexible kinematic constraints. ARDY employs a hybrid representation that combines explicit root features with a latent body embedding, balancing precise trajectory control with efficient generative learning. We propose a two-stage autoregressive transformer denoiser that features variable history context and supports conditioning on flexible, long-horizon kinematic constraints. By training on a large-scale motion capture dataset and being directly conditioned on text labels and kinematic constraints sampled from ground truth poses, ARDY natively learns controllable generation that supports online prompting and flexible long-horizon goals. Extensive evaluations on the HumanML3D benchmark and the large-scale, high-fidelity Bones Rigplay dataset demonstrate ARDY's high motion quality and constraint adherence, validating the efficacy of our key architectural decisions. Finally, we demonstrate the method's practical versatility through an interactive demo featuring dynamic text control, diverse keyframe pose constraints, path following, and interactive locomotion control via mouse and keyboard. Supplementary video results, code, and model releases can be found at https://research.nvidia.com/labs/sil/projects/ardy/.

2026-07-09T17:41:49Z ACM Transactions on Graphics (SIGGRAPH 2026) Kaifeng Zhao Mathis Petrovich Haotian Zhang Tingwu Wang Siyu Tang Davis Rempe 10.1145/3811284 http://arxiv.org/abs/2607.05667v1 2026-07-06T22:16:37Z

Gaussian-based image representations effectively model image content using compact parametric primitives while preserving high visual fidelity, yet storing a large number of floating-point parameters per primitive degrades rate-distortion efficiency at higher fidelity targets. To improve the rate-distortion performance in Gaussian representation, we present our Cluster-Guided Vector Quantization (CGVQ), a Gaussian primitive based image compression method. Our key idea is to partition Gaussian parameters further into homogeneous groups prior to quantization, enabling higher compression efficiency and accurate parameter reconstruction. In practice, our extensive experiments show that CGVQ decreases the bpp by 20% with respect to our baseline, while maintaining on-par visual quality

2026-07-06T22:16:37Z 3 pages. Accepted to ACM SIGGRAPH 2026 Poster Track. Code available at https://github.com/complight/Cluster_Guided_Vector_Quantization Runze Cheng Yicheng Zhan Josef Spjut Kaan Akşit http://arxiv.org/abs/2606.31579v1 2026-06-30T12:34:53Z

Boundary Representation (B-rep) is the most commonly used data format in Computer-Aided Design (CAD) due to its analytical precision and direct support for parametric editing. However, its heterogeneous structure--continuous parametric geometry combined with discrete topological graphs--poses fundamental challenges for deep learning. Existing methods often predict the heterogeneous B-rep graph directly, using fixed-size padding or sequential tokenization to handle varying primitive counts. These approaches struggle with the combinatorial complexity of CAD models. Furthermore, the discrete, non-differentiable nature of graph data prevents end-to-end optimization of geometry and watertightness. In this work, we introduce DualBrep, a novel continuous representation that unifies B-rep geometry and topology within a fully structured Euclidean domain. DualBrep encodes a CAD model using dual scalar fields: a Signed Distance Function (SDF) representing global shape geometry, and an Unsigned Distance Field (UDF) implicitly encoding topological structure via a Voronoi partitioning of surface elements. Rather than processing these fields independently, we compress them into a single latent space. While the dual-field formulation alone provides a flexible, primitive-free segmentation signal that adapts to arbitrary face counts and surface types, the shared latent makes generation tractable. A Flow Matching model can sample geometry and topology jointly from a single code, avoiding the error accumulation that plagues sequential B-rep predictors. Finally, a neural rebuilder extracts explicit B-rep models--comprising both prismatic and free-form primitives--directly from our continuous dual fields. We demonstrate that DualBrep is a robust backbone for CAD learning, achieving strong performance in point cloud reverse engineering and generative modeling via latent flow matching.

2026-06-30T12:34:53Z Published in SIGGRAPH 2026; Code is available at https://github.com/AutodeskAILab/DualBrep Yilin Liu Pradeep Jayaraman Chinthala Reddy Xiang Xu Hooman Shayani http://arxiv.org/abs/2606.25220v1 2026-06-23T22:34:34Z

Real-time texture transfer expands the creative horizon for interactive applications, enabling seamless detail projection in scenarios that range from digital character cosmetics to procedural automotive texturing. Yet, its practical application is governed by inherent trade-offs between processing speed and suppression of artifacts. Low-latency transfer methods frequently fail to suppress artifacts, and robust alternatives rely on large-scale models that are costly in training and memory. Our proposed method bridges the gap between efficiency and robustness by using a cage-based geometric filtering method to identify Non-Cosmetic Zones (NCZs) for artifact suppression. While other models are resource-intensive and require multiple days of training on manually annotated datasets, we are able to successfully suppress artifacts and achieve immediate deployment on consumer-grade hardware. Our framework achieved highly efficient runtimes of ~70ms on mobile devices for a ~4.8k triangle mesh.

2026-06-23T22:34:34Z Accepted to SIGGRAPH 2026 Rose Mei Zhou Lynnette Hui Xian Ng Adrian Xuan Wei Lim Conor Griffin Faraz Baghernezhad http://arxiv.org/abs/2606.23489v2 2026-08-21T13:14:19Z

Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains important symmetries, including permutation invariance of faces and vertices. MeshFlow learns to generate triangle meshes directly as triangle soups, avoiding the need to serialize meshes into long autoregressive sequences. We adopt equivariant optimal-transport flow matching models that respect the key symmetries of triangle soups: arbitrary permutations of faces and permutations of the vertices within each face. Toward this goal, we propose a simple yet effective modification to the Diffusion Transformer architecture, resulting in a scalable network capable of modeling a velocity field while maintaining the desired equivariance. We further introduce an optimal-transport-based training objective that improves convergence by eliminating supervision signals that violate these symmetries. MeshFlow achieves mesh quality comparable to state-of-the-art autoregressive mesh generators while providing about an 18$\times$ speedup during inference. Project page is at https://qiisun.github.io/MeshFlow/.

2026-06-22T15:35:30Z SIGGRAPH 2026 Qi Sun Kiyohiro Nakayama Jing Nathan Yan Qixing Huang Alexander Rush Leonidas Guibas Gordon Wetzstein Jing Liao Guandao Yang http://arxiv.org/abs/2606.23270v1 2026-06-22T12:49:29Z

As instruction-based editing models and multimodal large language models advance, diverse image editing tasks have become feasible. However, achieving precise and consistent geometric image editing, such as translating, scaling, and rotating in 3D space, remains a major challenge. In this work, we introduce BoxCtrl, a 3D-aware visual prompting framework. Unlike text-only or coarse 2D-guided approaches, our method introduces informative RGB 3D bounding boxes projected onto 2D images as visual prompts. The three orthogonal faces of each box are painted with distinct RGB colors, simultaneously encoding position, size, and orientation to provide a compact, intuitive in-context visual example. The key to BoxCtrl's success lies in these well-designed bounding boxes, which decouple geometric control from appearance control. This enables the model to learn consistent correspondences between faces of the same color in the latent space, leading to a precise understanding of geometric intentions and accurate editing results. We introduce a two-stage training paradigm: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL). To address paired data scarcity, we construct a large-scale synthetic dataset for SFT, equipping the model with fundamental editing capabilities. To bridge the synthetic-to-real domain gap, we incorporate an online RL stage leveraging unpaired real-world data. Guided by a reward function evaluating geometric accuracy and visual fidelity, our SFT-RL strategy significantly enhances geometric precision while maintaining photorealistic quality. Extensive experiments demonstrate that BoxCtrl achieves state-of-the-art performance across translation, rotation, scaling, and composite editing tasks.

2026-06-22T12:49:29Z Accepted by SIGGRAPH 2026 Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH Conference Papers 2026, Article 164, pp. 164:1-164:11, ACM, 2026 Feifei Wang Shiyuan Yang Xiaoyu Li Jing Liao 10.1145/3799902.3811169 http://arxiv.org/abs/2606.22880v1 2026-06-22T05:46:04Z

Representing complex geometry as a displacement function defined over a coarse base mesh enables compact storage and accelerated rendering. The core challenge in converting detailed triangle meshes into this representation is computing base meshes that have as few triangles as possible, while also supporting displacement functions that accurately approximate the input. Accurate approximation requires the supported displacement functions to bijectively map the input surface onto the base with low parametric distortion. We observe that this distortion can be measured by evaluating the pointwise Jacobian of the displacement functions. Our new DJM (Displacement Jacobian Metric)-based base-mesh construction method uses the Jacobian of the displacement functions to guide base mesh computation, enabling us to outperform prior approaches in terms of accuracy to size trade-off. We achieve this goal by proposing a variant of the QEM-based simplification scheme that constrains the displacement mapping between the input and the base to be bijective and low distortion (defined as satisfying a lower bound on the mapping Jacobian). When evaluating and encoding the displacement maps, we avoid unreliable ray-mesh intersections by explicitly storing the mapping between the input mesh and the base throughout the construction process, and use this mapping within a robust inverse barycentric displacement solver to obtain dense base-to-mesh correspondences to assist all computations. We demonstrate DJM to outperform alternative schemes in terms of reconstruction accuracy to size trade-off, and demonstrate its robustness and usability for micromesh-based rendering and neural encoding.

2026-06-22T05:46:04Z Accepted to SIGGRAPH 2026. Project page: https://www.cs.ubc.ca/labs/imager/tr/2026/djm Congyi Zhang Nicholas Vining Yanhong Lin Alireza Khatami Ziyu Sun Xiaohu Guo Wenping Wang Alla Sheffer http://arxiv.org/abs/2606.20891v1 2026-06-18T19:40:03Z

Filmmaking demands precise motion control and reference image compositing -- capabilities that existing methods treat separately. Point-track-conditioned image-to-video models restrict content insertion to the first frame, while reference-to-video models lack fine-grained spatial-temporal control over how reference content integrates across frames. We present Go-with-the-Track, which unifies both capabilities by jointly conditioning on multiple reference images and reference-anchored point-tracks -- extending conventional point-tracks to explicitly establish correspondences between generated frames and reference images, thus enabling precise compositing and motion control throughout the video. To achieve this, we introduce spatially-aware point-track embeddings that encode the full sequence of point-track coordinates using a coordinate-wise MLP followed by temporal pooling. This representation captures the spatial characteristics of each point-track (serving as a unique identifier), while the embedding similarity correlates directly with spatial proximity, enhancing the model's ability to distinguish and associate point-tracks. We inject these point-track embeddings into a video diffusion transformer via a lightweight adapter, resolving the pixel-to-patch resolution mismatch while avoiding the substantial motion detail loss inherent in naive point-track subsampling. We use a hybrid training strategy to train jointly on dynamic, static, and synthetic scene video datasets to boost motion controllability. Experiments demonstrate that Go-with-the-Track achieves superior motion and reference control in a single model and enables new capabilities: multi-reference conditioned video generation with point-track driven compositing, as well as camera control for both static and dynamic scenes. Project Page: https://eyeline-labs.github.io/Go-with-the-Track/

2026-06-18T19:40:03Z SIGGRAPH 2026, Project page: https://eyeline-labs.github.io/Go-with-the-Track/ Koichi Namekata Yash Kant Zhizheng Liu Ryan D Burgert Yuancheng Xu Kuan Heng Lin Emmett Steven Julien Philip Li Ma Andrea Vedaldi Paul Debevec Ning Yu http://arxiv.org/abs/2606.18243v1 2026-06-16T17:58:44Z

Collaborative human-object interaction shows dynamic and complex movements that require mutual anticipation and continuous adjustment between participants and the shared object. Modeling such collaborative multi-human object interaction (MHOI) scenarios requires high-quality data acquisition as a foundational step; however, this is challenging due to the inherent complexity of MHOI where human-human and human-object interactions occur simultaneously. Such complexity leads to noisy MHOI captures characterized by several artifacts: contact misalignment between hands and objects, motion jitter and temporal inconsistencies in the captured sequences, and missing or incomplete finger-level articulation details. To address these challenges, we present MOCHI (MOtion Enhancement of Collaborative Human-object Interactions), a two-stage framework for enhancing noisy MHOI data. Our approach first generates physically plausible hand grasps through optimization from noisy body input, producing grasps that are both physically plausible and semantically consistent with the body pose, where these optimized grasps are extended into complete hand-object interaction sequences. Consequently, the full-body motion for all participants are refined through a diffusion-based noise optimization framework that uses single-person motion priors. During the optimization process, we introduce optimization objectives to encode human-object and human-human interaction information within these single-person priors. Experimental results demonstrate the effectiveness of our pipeline across diverse MHOI data, either acquired by existing capture methods or synthesized by generative models. We further show robustness of our system across varying numbers of participants and types of interactions, and demonstrate various applications including keyframe-based MHOI creation and data augmentation through varying object geometries.

2026-06-16T17:58:44Z SIGGRAPH 2026 Journal (ACM TOG); Project page: https://jiyewise.github.io/projects/MOCHI/ Jiye Lee Yonghun Choi Jungdam Won 10.1145/3811308 http://arxiv.org/abs/2606.17935v1 2026-06-16T13:43:35Z

Online 3D reconstruction from monocular image sequences is a challenging and ongoing research topic. 3D Gaussian Splatting (3DGS), leveraging its high-quality real-time rendering capability, empowers online 3D reconstruction to represent dense scenes with enhanced expressiveness, and thus holds great promise for a wide range of applications such as robotics and AR/VR. However, existing online 3DGS methods still suffer from some key challenges: fragile camera pose estimation due to the lack of global optimization, and low optimization efficiency in large-scale or long-sequence scenarios. To address these issues, we propose a robust and efficient online voxelized 3DGS reconstruction framework integrated with global $\text{Sim}(3)$ optimization, which enables reliable camera tracking and efficient global loop closure for both camera poses and voxelized 3DGS. To accelerate the convergence of the voxelized 3DGS, we further introduce a color residual learning strategy, which not only boosts optimization speed but also enhances rendering quality. Extensive experiments on diverse indoor and outdoor datasets demonstrate that our method achieves state-of-the-art performance in both camera pose estimation accuracy and rendering quality, while retaining real-time efficiency. Additionally, we develop and deploy a real-world UAV-based active reconstruction system grounded on our proposed method, validating its robustness and generalizability for practical online 3D reconstruction tasks. Our code and data are available at https://github.com/TrickyGo/MoonSplat.

2026-06-16T13:43:35Z SIGGRAPH 2026 Guo Pu Yixuan Han Haofeng Li Yao Zhang Hui Zhou Zhouhui Lian http://arxiv.org/abs/2606.15238v1 2026-06-13T10:34:10Z

The fundamental limitation of traditional strand-based modeling is not simply data scarcity, but the ill-posedness of inferring complex 3D fields from 2D imagery without structural constraints. This unconstrained regression leads to catastrophic failures in resolving both global occlusion (e.g., in ponytails) and local directionality (e.g., in curls), resulting in over-smoothed, plausible-but-incorrect geometries. To resolve this, we integrate the strong geometric priors of Large Reconstruction Models (LRMs) into the strand generation pipeline. Using the LRM mesh as a structural anchor, we employ a novel Dual Orientation AutoEncoder to lift coarse geometry into high-fidelity strands. By resolving vector field singularities through latent-space optimization and surface-guided refinement, our method effectively disentangles complex topological structures, setting a new benchmark for robustness and accuracy in hair reconstruction.

2026-06-13T10:34:10Z ACM SIGGRAPH 2026 Conference Paper Yuefan Shen Yican Dong Xiufeng Huang Zhongtian Zheng Youyi Zheng Kui Wu http://arxiv.org/abs/2606.14173v2 2026-06-16T06:49:06Z

Holography offers unique advantages for delivering perceptual realism while preserving compact form factors in VR/AR. Its perceptual quality, however, hinges on encoding rich wavefronts of photorealistic scenes into interference patterns and then incoherently multiplexing the resulting wave fields for perception. Existing CGH paradigms decouple radiance estimation from wave propagation by pre-rendering radiance on discretized scene sectors. This separation between radiometric and wave-optical computation inherently limits the range of focus cues and visual effects that can be faithfully reproduced, including depth- and view-continuity, and physically based material behaviors such as glossy or mirror-like reflection and refraction. We present a physically accurate yet computationally efficient wave optics rendering framework leveraging path tracing to encode full 3D visual cues into phase holograms. Specifically, we employ a Monte Carlo method to solve both the rendering equation and the Rayleigh--Sommerfeld integral simultaneously. Our algorithm is fully compatible with modern graphics techniques and can generate multiple time-multiplexed random holograms with minimal additional time cost via Path Reuse. By employing a fast approximation with an ambient radiance cache, we realize an order of magnitude convergence speed improvement. The resulting coherent wave fields that inherently encode comprehensive visual effects are converted into phase-only holograms under complex-amplitude supervision. Through extensive simulations and experimental validations on a spatial light modulator-based display prototype, we demonstrate faithful holographic reconstructions of natural 3D cues and complex materials, including realistic defocus blur, view-dependent effects, as well as appearance highlights and reflections.

2026-06-12T06:54:35Z ACM Transactions on Graphics, Vol. 45, No. 4, Article 39, July 2026, 12 pages. Presented at SIGGRAPH 2026 ACM Trans. Graph. 45, 4, Article 39 (July 2026), 12 pages Wenbin Zhou Xiangyu Meng Jiankai Xing Xin Liu Suyeon Choi Yifan Peng 10.1145/3811351 http://arxiv.org/abs/2606.12562v2 2026-07-17T20:14:18Z

Transferring hairstyles between images is an important but challenging task in computer graphics, computer vision, and visual effects. It enables users to explore new looks without physically altering their hair, with applications in virtual try-on systems, augmented reality, and entertainment. Most prior works operate best under small pose gaps, and they fall short under large viewpoint and scale differences, where missing hair content must be synthesized rather than transferred. We propose HairPort, a 3D-aware hairstyle transfer framework that attempts to solve these issues by explicitly separating hair removal from transfer and enforcing geometric consistency before synthesis. We introduce a Bald Converter, which produces realistic bald versions of faces through LoRA-based in-context adaptation of FLUX.1 Kontext. To train our Bald Converter, we introduce a new dataset, Baldy, containing 6,000 paired bald and original images across diverse identities and conditions. We also use a 3D-Aware Transfer Pipeline that reconstructs and re-renders the reference hairstyle from the target viewpoint before compositing it onto the source image. Being 3D aware, our method supports large pose and scale discrepancies between the source and target. Finally, a conditional flow-matching generator synthesizes the transferred result from the bald source and geometry-aligned reference guidance. Together, our method enables accurate, pose-consistent, and identity-preserving hairstyle transfer, outperforming existing methods both qualitatively and quantitatively.

2026-06-10T18:13:18Z Accepted to SIGGRAPH 2026 (Conference Papers Track). 23 pages, 15 figures, 10 tables, including supplementary material as appendices. Project page: https://deepmancer.github.io/HairPort/ Alireza Heidari Amirhossein Alimohammadi Ali Mahdavi-Amiri 10.1145/3799902.3811046 http://arxiv.org/abs/2606.06901v1 2026-06-05T04:34:47Z

Photography is the art of painting with light, yet nighttime scenes are shaped by competing degradations: intense flares obscure scene structure, while photon-limited regions collapse into noise. Conventional approaches address these factors in isolation, overlooking the fact that these degradations are fundamentally entangled. To bridge this gap, we introduce LUCID, a unified framework that reframes nighttime restoration as a continuous and controllable process rather than a fixed correction. We decompose nighttime restoration into two cooperative components: a flare disentanglement module that lifts the 'curtain' of optical artifacts to provide reliable structural guidance, and a diffusion-driven module that leverages generative priors to reconstruct clean and well-exposed imagery. Crucially, LUCID introduces explicit controllability through a novel four-mode training strategy, enabling users to steer the restoration process via classifier-free guidance (CFG) and allowing selective control over light sources and their associated flare and ghosting artifacts, while also supporting high dynamic range (HDR) reconstruction through continuous exposure control. Extensive experiments demonstrate that LUCID consistently outperforms state-of-the-art methods across diverse real-world nighttime scenarios.

2026-06-05T04:34:47Z Accepted by SIGGRAPH 2026 Tingyu Yang Yuan Cheng Xiaoyun Yuan http://arxiv.org/abs/2606.04880v1 2026-06-02T17:59:57Z

Selection is a core operation in interactive image editing. To be practical, a user should be able to specify and disambiguate the desired selection region through either text or click-based interactions, and the system should support selecting not only objects but also other criteria, such as materials. Material-based selection is valuable for tasks like re-texturing surfaces or editing instances of a specific material. However, existing vision-language-model (VLM) based selection methods are object-centric and typically support a single interaction modality, limiting their applicability. In this work, we thus present Mask Any Object And Material (MAOAM), a unified selection framework that enables precise object and material-level selection across both text- and click-based interactions. MAOAM leverages a VLM with a segmentation head to produce pixel-accurate masks from user prompts: the VLM interprets the user's selection intent (object or material-level) and encodes visual entities, attributes, and spatial relations, while the segmentation head decodes the output token into a mask. A key challenge is the lack of material selection datasets with text annotations. We propose a scalable data generation pipeline: we collect real and synthetic images with material masks, and leverage VLMs to generate material descriptions with rich visual-semantics. We train MAOAM with a multi-task objective over click and text-based selection, along with an auxiliary VQA task derived from the material descriptions to facilitate deeper material understanding. Despite being trained with uni-modal prompts, our model exhibits an emergent improvement in selection when combining text and clicks at inference, enabling flexible image editing workflows. Experiments demonstrate accurate and coherent selections across diverse objects, materials, and interaction scenarios, highlighting robustness in practice.

2026-06-02T17:59:57Z Accepted to SIGGRAPH 2026 Conference. Project page: \href{https://jadenpark0.github.io/project_pages/maoam/}{here} Jaden Park Valentin Deschaintre Jason Kuen Kangning Liu Iliyan Georgiev Krishna Kumar Singh Yong Jae Lee Michael Fischer 10.1145/3799902.3811186 http://arxiv.org/abs/2606.02919v3 2026-06-05T00:48:04Z

We present a diffusion-based method for relighting dynamic portrait videos with photorealism and temporal consistency. Our method is fueled by a hybrid training dataset that consists of real-captured and rendered dynamic portrait videos with diverse subject appearances, facial motions, head poses, and known lighting conditions. Specifically, we construct an LED-based lighting system for realistic lighting emulation and high-speed video relighting data acquisition. By leveraging the image priors embedded in pre-trained video diffusion models, and using per-frame high dynamic range (HDR) environment map as lighting control, we train a high-performance generative model for realistic and identity-preserving dynamic portrait video relighting. In addition to the environment map control, our model uses a synthesized background image to enable control on the camera's exposure level and color tone. Our model can produce temporally consistent relit portrait video that looks realistic and harmonious under a provided new environment and faithfully preserve the subject's expression and fine facial features, including skin tone, wrinkles, and facial hair. Our model generalizes well to unseen data, in terms of the subject appearance, motion, and lighting condition. We perform extensive experiments on relighting in-the-wild videos with various environment maps and demonstrate practical applications on portrait photography. Results show that our method achieves state-of-the-art performance in photorealism, lighting harmony, and temporal consistency.

2026-06-01T21:47:17Z ACM SIGGRAPH 2026 Journal Track / ACM Transactions on Graphics, 17 pages. Project page: https://yufanzhang82.github.io/PixelCube/ ACM Trans. Graph. 45, 4, Article 119 (July 2026), 17 pages Yufan Zhang Yu Ji Ayo Ajiboye Rundi Wu Yu Guo Changxi Zheng Jinwei Ye 10.1145/3811400 http://arxiv.org/abs/2605.30925v1 2026-05-29T07:14:48Z

Text-to-motion generation has progressed rapidly in recent years, offering an expressive interface for animation and human-computer interaction. However, current models remain brittle when handling prompts that describe multiple actions occurring at the same time. Rather than realizing all components of a composite description, models frequently prioritize a single dominant action and neglect the rest, leading to incomplete or ambiguous motion. We present MultiAct, an unpaired, inference-time framework for compositional text-to-motion synthesis that operates directly on pretrained motion generators without retraining or architectural modification. Our method counteracts semantic collapse by adaptively amplifying cross-attention scores associated with underrepresented prompt components. We note that effective modulation depends on prompt-specific choices, such as which tokens and layers to target, and introduce a lightweight auxiliary decision scheme that determines the most effective attention-strengthening parametrization. Extensive quantitative and qualitative evaluations demonstrate that MultiAct consistently outperforms existing baselines on composite prompts, achieving improved semantic coverage while preserving motion realism. Project page: https://natsala13.github.io/multiact.github.io.

2026-05-29T07:14:48Z Accepted to SIGGRAPH 2026 conference. Project page: https://natsala13.github.io/multiact.github.io Nathan Sala Ofir Abramovich Ariel Shamir Daniel Cohen-Or Andreas Aristidou Sigal Raab http://arxiv.org/abs/2605.28763v1 2026-05-27T17:22:38Z

Interactive 3D assets used in games and simulation are typically decomposed into specific semantic parts to support animation, physics, and scripted behaviors, yet most generative 3D models produce either monolithic meshes or arbitrary part decompositions that cannot be aligned with application-specific requirements. We present CubePart, a generative framework for open-vocabulary, part-controllable 3D mesh generation that exposes part structure as an explicit inference-time control signal. Given a global text prompt and a user-defined parts schema expressed as an open-ended list of part names, our method generates a set of meshes - one per schema element - that assemble into a coherent object while respecting the specified semantic structure. To enable this capability, we introduce a scalable data pipeline to construct a large open-vocabulary, part-labeled 3D dataset, along with a two-stage generative architecture that separates global shape synthesis from part-level decoding. We demonstrate that the resulting assets can be directly integrated into game engines and driven by animation and behavior scripts without manual post-processing. Project Page: https://cubepart.github.io/

2026-05-27T17:22:38Z SIGGRAPH 2026. Project Page: https://cubepart.github.io/ Yiheng Zhu Kangle Deng Jean-Philippe Fauconnier Inaki Navarro Daiqing Li Ava Pun Yinan Zhang Peiye Zhuang Xiaoxia Sun Maneesh Agrawala Kiran Bhat Tinghui Zhou http://arxiv.org/abs/2605.28272v1 2026-05-27T10:18:16Z

Real-time synthesis of high-fidelity 3D character motion from audio is a pivotal component for next-generation interactive avatars and virtual assistants. However, most existing approaches are limited to offline processing of complete audio sequences or are constrained to specific domains, rarely handling both speech and music effectively. In this paper, we introduce a novel framework designed to generate continuous, coherent full-body motion from streaming speech and music with low latency. Central to our approach is a unified streaming architecture capable of synthesizing continuous motion from incremental audio inputs. We employ a robust training strategy that enforces strong audio dependency, allowing the model to seamlessly generalize across conversational speech and rhythmic music without requiring explicit domain labels or mode switching. Additionally, we explored Reinforcement Learning to refine the quality of online generation. Furthermore, we bridge reactive animation with intent-driven behavior via a tool-call interface that allows upstream Large Language Models to inject explicit semantic control. By combining this controllability with stream audio-driven synthesis, our framework serves as a plug-and-play solution for transforming voice agents into interactive humanoid avatars. Extensive experiments demonstrate that our method outperforms state-of-the-art realtime baselines in motion quality and synchronization while maintaining the flexibility required for live deployment. Our code, pre-trained models, and videos are available at https://robinwitch.github.io/EchoAvatar-Page.

2026-05-27T10:18:16Z SIGGRAPH 2026; Project Page: https://robinwitch.github.io/EchoAvatar-Page Bohong Chen Yumeng Li Yinglin Xu Youyi Zheng Yanlin Weng Kun Zhou http://arxiv.org/abs/2605.25426v1 2026-05-25T04:57:25Z

We present a differentiable framework to automatically learn view-dependent 2D kernels in a splatting-based pipeline to improve reconstruction quality and representation efficiency for novel 3D view synthesis. Our volumetric primitive is defined as a bounding ellipsoid and a 3D-kernel latent vector. We first learn a projection network to output a 2D-kernel latent, taking the attributes of the ellipsoid and the 3D-kernel latent as input. Next, the result is sent to a decoder to produce a radially symmetric 2D kernel in terms of Mahalanobis distance, bounded by the projected ellipsoid. The neural networks along with per-primitive attributes are jointly optimized. The effectiveness of our approach is demonstrated on standard benchmarks, comparing favorably against state-of-the-art techniques on both analytical and learned kernels. Finally, we extend the idea to learn general 2D kernels for 2D splatting as well as image representation.

2026-05-25T04:57:25Z Accepted to SIGGRAPH 2026. 10 pages, 8 figures Huakeng Ding Zhanpeng Liu Fan Pei Kun Zhou Hongzhi Wu http://arxiv.org/abs/2605.24894v1 2026-05-24T06:46:52Z

As generative models expand the possibilities of visual content creation, layered image synthesis has emerged as a promising direction for controllable and creative editing. However, existing methods struggle to fully realize this potential. Decomposition-based methods often struggle with clean separation, while generation-based methods suffer from difficulty in training data acquisition, reducing quality and scene diversity. In this paper, we propose BFS, a novel generation-based framework for layered image synthesis. Specifically, given a background image and user guidance, BFS synthesizes a foreground layer that incorporates not only a foreground object but also its associated visual effects, such as shadows and reflections, while seamlessly harmonizing with the background to produce a coherent composite. To enable diverse and high-quality foreground layer synthesis while overcoming data scarcity, we leverage the comparatively easy-to-learn knowledge of unlayered image synthesis for the foreground synthesis. To this end, we adopt a dual-branch diffusion framework in which two interconnected branches generate a composite image and a foreground layer, respectively, enabling bidirectional knowledge transfer. Based on this framework, we propose a two-stage training scheme that utilizes a high-quality unlayered composite image dataset to effectively enhance foreground quality. Extensive experiments, including a user study, show that BFS produces high-quality layered images, consistently outperforming prior methods.

2026-05-24T06:46:52Z SIGGRAPH 2026 Kyoungkook Kang Gyujin Sim Sunghyun Cho http://arxiv.org/abs/2605.24488v2 2026-06-11T16:42:25Z

Content moderation in online multiplayer 3D virtual environments is increasingly automated, yet detection has focused on images, video, and audio, leaving suggestive motion a blind spot. We present a motion-only classification pipeline that detects suggestive and explicit movement from SMPL skeleton trajectories using Laban Movement Analysis (LMA) descriptors. On a dataset spanning everyday, artistic, suggestive, and explicit movement (17+ hours of video), a logistic regression trained on 61-feature LMA descriptors reaches 68% binary SFW/NSFW accuracy (70% random forest) under a leak-free evaluation protocol. At this level, our descriptor performs comparably to a learned video model trained on the same motion re-rendered as appearance-free video, a gray figure with no clothing, skin, or scene. The indirectness (tortuosity) of each joint's trajectory, measured as the ratio of the joint's path length to its net displacement, peaks at the suggestive tier, showing that the Direct-to-Indirect polarity of Laban's Space factor provides an interpretable marker of the shift from functional to suggestive motion. Ultimately, Laban-based kinematic descriptors offer a lightweight, interpretable approach to suggestive-motion detection: every decision decomposes into named, theory-grounded features. Because the classifier operates on pose trajectories alone, moderation can run directly on avatar poses in virtual environments, with no appearance data.

2026-05-23T09:22:32Z 5 pages, 2 figures, 3 tables. Extended version of a poster accepted to SIGGRAPH 2026 Jaehoon Ahn Jeonghan Kong Moon-Ryul Jung 10.1145/3799825.3818709 http://arxiv.org/abs/2605.23088v1 2026-05-21T22:39:21Z

Incremental Potential Contact (IPC) enables robust, contact-rich simulation by casting elasticity and contact as a single energy minimization problem, but high-performance IPC pipelines are typically built from specialized kernels and assembly logic tied to fixed energies, primitive types, and parameterizations, making extensions costly and combinatorial. We present YASPS, a GPU-oriented framework that removes this extensibility bottleneck by making structure explicit in a differentiable intermediate representation. YASPS introduces two first-class relational operators: JOIN, which composes dependent quantities across user-declared relations (e.g., element-to-vertex connectivity), and UNION, which represents alternative parameterizations within a relation (e.g., mixing free vertices with affine-body or other parameterizations without fragmenting the program). Because JOIN and UNION are part of the symbolic program, YASPS differentiates through them using dedicated rules and an efficient second-order procedure that reuses intermediate Jacobians and reduces Hessian-projection cost. From the same relational description, YASPS derives the global gradient/Hessian sparsity and block layout, enabling structure-aware block-sparse storage and compression, and JIT-compiles CUDA kernels for evaluation, derivatives, assembly, and solving. Across IPC-style examples, including layered cloth-on-bunny, mixed rigid/deformable bunnies, and a caged deformation model, YASPS supports rapid front-end extensions with minimal back-end changes while achieving competitive end-to-end performance; its Hessian compression yields near 10x faster CG iterations in our benchmarks.

2026-05-21T22:39:21Z Accepted to Siggraph 2026 Xuan Tang Kemeng Huang Gilbert Bernstein Minchen LI Tzumao Li 10.1145/3811327 http://arxiv.org/abs/2605.22051v1 2026-05-21T06:38:22Z

Generating high-fidelity visual effects (VFX) typically demands massive datasets and prohibitive computational power due to the intricate coupling of spatial textures and temporal dynamics. In this paper, we introduce EasyVFX, a resource-efficient framework that achieves realistic VFX synthesis under stringent constraints. Our core philosophy lies in frequency-domain decomposition: we observe that the complexity of VFX can be significantly mitigated by decoupling high-frequency components, which represent intricate spatial appearances, from low-frequency components that encapsulate global motion dynamics. This spectral disentanglement transforms a high-dimensional learning problem into manageable sub-tasks, thereby lowering the optimization barrier and reducing data dependency. Building upon this insight, we propose a two-stage training paradigm. First, we design a Frequency-aware Mixture-of-Experts (Freq-MoE) architecture. By utilizing a soft routing mechanism, our model assigns specialized experts to distinct spectral bands, enabling them to cultivate robust priors for appearance and motion dynamics. This specialization allows the model to acquire foundational VFX knowledge with fewer GPU resources. Second, we introduce a Test-Time Training strategy powered by a novel Frequency-constraint Loss. This allows the pre-trained model to swiftly adapt to specific, unseen effects through localized optimizations, requiring only about 100 steps on a single GPU. Experimental results demonstrate that EasyVFX produces structurally consistent and visually stunning effects, proving that frequency-aware learning is a key catalyst for democratizing professional-grade VFX.

2026-05-21T06:38:22Z Accepted by SIGGRAPH 2026. Project page: https://easy-vfx.github.io/ Yue Ma Xu Ye Qinghe Wang Yucheng Wang Hongyu Liu Yinhan Zhang Xinyu Wang Yuanpeng Che Shanhui Mo Paul Liang Fangneng Zhan Qifeng Chen http://arxiv.org/abs/2605.21766v1 2026-05-20T21:57:31Z

Being able to relight human performance is a fundamental task for post production and content creation. We present BodyReLux, a subject-specific video diffusion-based framework for relighting full-body human performances in a temporally consistent way. Our model is trained on a hybrid dataset of pixel-aligned video relighting pairs, covering a diverse combination of lighting conditions, performances and viewpoints. To acquire such dataset, we combine traditional static One-Light-at-a-Time (OLAT) capture and a novel dynamic performance capture in which two smoothly varying lighting sequences are rapidly interleaved. Because the lighting operates above the human flicker-fusion threshold, the interleaving does not appear to strobe. We train our video relighting model from a pretrained text-to-video model to fully leverage the generative priors for producing high quality videos. To achieve accurate lighting control, we introduce a new lighting conditioning method that represents each light source as a token. We further condition on sequences of lighting using masked attention to support dynamic lighting control. Together with a carefully designed data augmentation pipeline, we achieve photorealistic, robust, and temporally consistent video relighting of subject-specific human performances.

2026-05-20T21:57:31Z Siggraph 2026 Journal Track. Project page: https://eyeline-labs.github.io/bodyrelux/ Li Ma Mingming He Xueming Yu David M. George Ahmet Levent Taşel Paul Debevec Julien Philip 10.1145/3811352 http://arxiv.org/abs/2605.20872v1 2026-05-20T08:08:39Z

Adaptive densification is the engine of 3D Gaussian Splatting (3DGS). However, when transposed to the optimization-based Generative Distillation paradigm, this reconstruction-native mechanism reveals fundamental limitations, resulting in inefficient representations cluttered with redundant primitives. We diagnose this failure as a Densification Dilemma stemming from the stochastic nature of generative guidance: the standard magnitude-based accumulation indiscriminately aggregates transient noise alongside geometric signals, making it difficult to strike a balance between over-densification and under-fitting. To resolve this, we introduce Context-Adaptive Moment Estimation (CAdam), a novel framework that reinterprets densification as a statistically grounded signal verification problem. CAdam leverages the first moment of gradients to exploit the interference principle, where stochastic fluctuations cancel out via destructive interference while consistent geometric drifts accumulate via constructive interference, effectively disentangling the underlying signal from the generative noise floor. This is further augmented by a quantile-based context awareness and an intrinsic Signal-to-Noise Ratio (SNR) gating mechanism, which ensure robust adaptation across optimization stages and enable the soft termination of densification. Extensive experiments across diverse objectives (SDS, ISM, VFDS) and strong generative 3DGS backbones show that CAdam reduces Gaussian count by 85%-97% relative to standard densification while preserving overall comparable perceptual quality. These results highlight signal-aware density control as a practical way to improve memory efficiency in optimization-based generative distillation.

2026-05-20T08:08:39Z Accepted to SIGGRAPH 2026 Conference Papers. 12 pages, 8 figures SeungJeh Chung Geonho Park Misong Kim HyeongYeop Kang 10.1145/3799902.3811215 http://arxiv.org/abs/2605.19355v1 2026-05-19T04:41:11Z

Retargeting motion across characters with varying body shapes while preserving interaction semantics, such as self-contact and near-body proximity, remains a challenging problem. While recent geometry-aware approaches address this by maintaining spatial relationships between predefined corresponding regions, their reliance on static correspondences often struggles when the target character exhibits exaggerated body proportions. In this paper, we present a geometry-aware motion retargeting framework that preserves interaction semantics by performing proximity matching over spatially adaptive anchors. Unlike prior methods with static anchor definitions, the proposed method dynamically repositions anchors to reachable regions on the target character. This is achieved via a Transformer-based anchor refinement strategy that predicts anchor displacements and constrains the translated anchors to remain on the target character geometry through differentiable soft projection. By incorporating pose-dependent spatial structures from the source character, the adapted anchors provide structurally coherent guidance for interaction-aware retargeting. Conditioned on these anchors, a graph-based autoencoder predicts target skeletal motion that preserves the spatial configuration of the source. To encourage task-aligned optimization between anchor adaptation and motion retargeting, we adopt an alternating training scheme in which each module is optimized in turn. Through extensive evaluations, we demonstrate that our method outperforms state-of-the-art approaches in preserving interaction fidelity across diverse character geometries.

2026-05-19T04:41:11Z SIGGRAPH 2026 / ACM TOG. Project page available at https://suzyn.github.io/space_page/ Soojin Choi Seokhyeon Hong Chaelin Kim Junghyun Nam Junhyuk Jeon Junyong Noh http://arxiv.org/abs/2605.19305v1 2026-05-19T03:33:52Z

This paper tackles the task of learning to generate signals over triangle meshes in a triangulation-agnostic manner, meaning the trained model can be applied to different meshes and triangulations effectively. Practically, the paper adapts the flow matching (FM) paradigm to a mesh-based, triangulation-agnostic setting. Theoretically, it proposes a specific noise distribution which is triangulation agnostic, to be used inside the FM model's denoising process. While noise distributions are usually trivial to devise for, e.g., images, devising a triangulation-agnostic distribution proves to be a much more difficult task. We formulate a mathematical definition of triangulation agnosticism of distributions, via their spectrum. We then show that a discretization of a specific Gaussian random field called a Matérn process holds these desired properties, and provides a simple and efficient sampling algorithm. We use it as our noise model, and adapt FM to the triangulation-agnostic setting by using a state-of-the-art approach for learning signals on meshes in the gradient domain -- PoissonNet -- as the denoiser. We conduct experiments on elaborate tasks such as sampling elastic rest states, and generating poses of humanoids. Our method is shown to be capable of producing highly realistic results for meshes of over one million triangles, significantly exceeding the state-of-the-art in quality and diversity.

2026-05-19T03:33:52Z In ACM Transactions on Graphics (SIGGRAPH 2026). Project page: https://matern-fm.github.io/ Tianshu Kuai Arman Maesumi Daniel Ritchie Noam Aigerman http://arxiv.org/abs/2605.13838v3 2026-06-27T12:19:23Z

Video-guided 3D animation holds immense potential for content creation, offering intuitive and precise control over dynamic assets. However, practical deployment faces a critical yet frequently overlooked hurdle: the pose misalignment dilemma. In real-world scenarios, the initial pose of a user-provided static mesh rarely aligns with the starting frame of a reference video. Naively forcing a mesh to follow a mismatched trajectory inevitably leads to severe geometric distortion or animation failure. To address this, we present Rectified Dynamic Mesh (R-DMesh), a unified framework designed to generate high-fidelity 4D meshes that are ``rectified'' to align with video context. Unlike standard motion transfer approaches, our method introduces a novel VAE that explicitly disentangles the input into a conditional base mesh, relative motion trajectories, and a crucial rectification jump offset. This offset is learned to automatically transform the arbitrary pose of the input mesh to match the video's initial state before animation begins. We process these components via a Triflow Attention mechanism, which leverages vertex-wise geometric features to modulate the three orthogonal flows, ensuring physical consistency and local rigidity during the rectification and animation process. For generation, we employ a Rectified Flow-based Diffusion Transformer conditioned on pre-trained video latents, effectively transferring rich spatio-temporal priors to the 3D domain. To support this task, we construct Video-RDMesh, a large-scale dataset of over 500k dynamic mesh sequences specifically curated to simulate pose misalignment. Extensive experiments demonstrate that R-DMesh not only solves the alignment problem but also enables robust downstream applications, including pose retargeting and holistic 4D generation.

2026-05-13T17:58:13Z Accepted by SIGGRAPH 2026, Project Page: https://r-dmesh.github.io/ Code URL: https://github.com/Tencent-Hunyuan/R-DMesh Zijie Wu Lixin Xu Puhua Jiang Sicong Liu Chunchao Guo Xiang Bai 10.1145/3799902.3811135 http://arxiv.org/abs/2605.13333v1 2026-05-13T10:51:54Z

Text-driven motion diffusion models are capable of generating realistic human motions, but text alone often struggles to express fine-level nuances of motion, commonly referred to as style. Recent approaches have tackled this challenge by attaching a style injection mechanism to a pretrained text-driven diffusion model. Existing stylization methods, however, either require style-specific fine-tuning of existing models or rely on heavy ControlNet-based architectures, limiting efficiency and generalization to unseen styles. We propose a lightweight style conditioning framework that dynamically modulates a pretrained diffusion model through hypernetwork-generated LoRA parameters. A style reference motion is encoded into a global style embedding, which is mapped by a hypernetwork to low-rank updates applied at each denoising step of the diffusion model. By structuring the style latent space with a supervised contrastive loss, our framework reliably captures diverse stylistic attributes, improves generalization to unseen styles, and supports optimization-based guidance without requiring predefined style categories. Experiments on the HumanML3D and 100STYLE datasets show state-of-the-art stylization results, while achieving improved stylization for unseen styles.

2026-05-13T10:51:54Z Accepted to SIGGRAPH 2026. Project page: https://junhyukjeon.github.io/projects/style-salad/ Junhyuk Jeon Seokhyeon Hong Junyong Noh http://arxiv.org/abs/2605.13293v1 2026-05-13T10:06:41Z

Boundary Representation (BRep) is the standard format for Computer-Aided Design (CAD), yet reconstructing high-quality BReps from single-view images remains challenging due to the complexity of topological constraints and operation sequences. We present Img2CADSeq, a multi-stage pipeline that overcomes these limitations by encoding CAD sequences into a three-level hierarchical codebook. Guided by an importance prioritization, this strategy values profiles over details, compressing long sequences into a stable discrete latent space. To bridge the modality gap, we leverage a coarse-to-fine point cloud intermediate, aligning 2D visual features with 3D CAD sequences via contrastive learning to condition a VQ-Diffusion model. Supported by newly introduced CAD-220K and PrintCAD datasets, our approach ensures robust industrial domain adaptation. Extensive experiments demonstrate that Img2CADSeq significantly outperforms state-of-the-art methods, producing standard STEP files that can be directly used in commercial CAD software.

2026-05-13T10:06:41Z Accepted by SIGGRAPH 2026 Conference Shiyu Tan Zixuan Zhao Hao Gao Zhiheng Chen Xiaolong Yin Enya Shen 10.1145/3799902.3811174 http://arxiv.org/abs/2605.12498v1 2026-05-12T17:59:56Z

Reconstructing the absolute 3D pose and shape of the hands from the user's viewpoint using a single head-mounted camera is crucial for practical egocentric interaction in AR/VR, telepresence, and hand-centric manipulation tasks, where sensing must remain compact and unobtrusive. While monocular RGB methods have made progress, they remain constrained by depth-scale ambiguity and struggle to generalize across the diverse optical configurations of head-mounted devices. As a result, models typically require extensive training on device-specific datasets, which are costly and laborious to acquire. This paper addresses these challenges by introducing EgoForce, a monocular 3D hand reconstruction framework that recovers robust, absolute 3D hand pose and its position from the user's (camera-space) viewpoint. EgoForce operates across fisheye, perspective, and distorted wide-FOV camera models using a single unified network. Our approach combines a differentiable forearm representation that stabilizes hand pose, a unified arm-hand transformer that predicts both hand and forearm geometry from a single egocentric view, mitigating depth-scale ambiguity, and a ray space closed-form solver that enables absolute 3D pose recovery across diverse head-mounted camera models. Experiments on three egocentric benchmarks show that EgoForce achieves state-of-the-art 3D accuracy, reducing camera-space MPJPE by up to 28% on the HOT3D dataset compared to prior methods and maintaining consistent performance across camera configurations. For more details, visit the project page at https://dfki-av.github.io/EgoForce.

2026-05-12T17:59:56Z 23 pages, 19 figures and 10 tables; project page: https://dfki-av.github.io/EgoForce (source code, data and demo available); SIGGRAPH 2026 Conference Christen Millerdurai Shaoxiang Wang Yaxu Xie Vladislav Golyanik Didier Stricker Alain Pagani http://arxiv.org/abs/2605.12399v1 2026-05-12T17:00:47Z

3D Gaussian Splatting (3DGS) has emerged as a prominent paradigm for 3D reconstruction and novel view synthesis. However, it remains vulnerable to severe artifacts when trained under sparse-view constraints. While recent methods attempt to rectify artifacts in rendered views using image diffusion models, they typically rely on multi-view self-attention to retrieve information from reference images. We observe that this mechanism often fails when the rendered novel views output by 3DGS are heavily corrupted: damaged query features lead to erroneous cross-view retrieval, resulting in inconsistent rendering refinement. To address this, we propose GeoQuery, a geometry-guided diffusion framework that integrates generative priors with explicit geometric cues via a novel Geometry-guided Cross-view Attention (GCA) mechanism. First, by leveraging predicted depth maps and camera poses, we construct a geometry-induced correspondence field to sample reference features, forming a geometry-aligned proxy query that replaces the corrupted rendering features. Furthermore, we design a new cross-view feature aggregation pipeline, in which we restrict the cross-view attention to a local window around each proxy query to effectively retrieve useful features while suppressing spurious matches. GeoQuery can be seamlessly integrated into existing diffusion-based pipelines, enabling robust reconstruction even under extreme view sparsity. Extensive experiments on sparse-view novel view synthesis and rendering artifact removal demonstrate the effectiveness of our approach.

2026-05-12T17:00:47Z Accept to SIGGRAPH 2026 Conference Track Xiao Cao Yuze Li Youmin Zhang Jiayu Song Cheng Yan Wen Li Lixin Duan http://arxiv.org/abs/2605.10922v1 2026-05-11T17:55:04Z

Recent advances in 3D generative models have rapidly improved image-to-3D synthesis quality, enabling higher-resolution geometry and more realistic appearance. Yet fidelity, which measures pixel-level faithfulness of the generated 3D asset to the input image, still remains a central bottleneck. We argue this stems from an implicit 2D-3D correspondence issue: most 3D-native generators synthesize shape in canonical space and inject image cues via attention, leaving pixel-to-3D associations ambiguous. To tackle this issue, we draw inspiration from 3D reconstruction and propose Pixal3D, a pixel-aligned 3D generation paradigm for high-fidelity 3D asset creation from images. Instead of generating in a canonical pose, Pixal3D directly generates 3D in a pixel-aligned way, consistent with the input view. To enable this, we introduce a pixel back-projection conditioning scheme that explicitly lifts multi-scale image features into a 3D feature volume, establishing direct pixel-to-3D correspondence without ambiguity. We show that Pixal3D is not only scalable and capable of producing high-quality 3D assets, but also substantially improves fidelity, approaching the fidelity level of reconstruction. Furthermore, Pixal3D naturally extends to multi-view generation by aggregating back-projected feature volumes across views. Finally, we show pixel-aligned generation benefits scene synthesis, and present a modular pipeline that produces high-fidelity, object-separated 3D scenes from images. Pixal3D for the first time demonstrates 3D-native pixel-aligned generation at scale, and provides a new inspiring way towards high-fidelity 3D generation of object or scene from single or multi-view images. Project page: https://ldyang694.github.io/projects/pixal3d/

2026-05-11T17:55:04Z SIGGRAPH 2026. Project page: https://ldyang694.github.io/projects/pixal3d/ Dong-Yang Li Wang Zhao Yuxin Chen Wenbo Hu Meng-Hao Guo Fang-Lue Zhang Ying Shan Shi-Min Hu http://arxiv.org/abs/2605.09279v1 2026-05-10T03:08:24Z

Volumetric video (VV) streaming enables real-time, immersive access to remote 3D environments, powering telepresence, ecological monitoring, and robotic teleoperation. These applications turn VV streaming into a real-time interface to remote physical environments, imposing new system-level demands for photorealistic scene representation, low-latency interaction, and robust performance under heterogeneous networks. 3D Gaussian Splatting (3DGS) has been widely used for real-time photorealistic rendering, offering superior visual quality and rendering performance, but it faces challenges due to bandwidth consumption. Furthermore, as the foundation of adaptive VV streaming, existing Levels of Detail (LoD) methods based on density are not well-suited to Gaussian representations, leading to visible gaps and severe quality degradation. Recent studies have also explored attribute compression techniques to reduce bandwidth consumption. Our preliminary studies reveal that aggressive attribute compression primarily causes color distortion, which can be effectively corrected in the rendered image using a reference image. Motivated by these findings, we propose a novel Color-Adaptive scheme for adaptive VV streaming that uses vector quantization (VQ) to establish LoDs and correct color distortions with low-resolution reference images. We further present CAGS, an adaptive VV streaming system compatible with diverse Gaussian representations, which integrates the Color-Adaptive scheme by rendering reference images on the streaming server and performing color restoration on the client. Extensive experiments on our prototype system demonstrate that CAGS outperforms the existing adaptive streaming systems in PSNR by 5$\sim$20 dB under fluctuating bandwidth, operates significantly faster than existing scalable Gaussian compression methods, and generalizes across different Gaussian representations.

2026-05-10T03:08:24Z SIGGRAPH 2026 Conference Paper. Code is available at https://github.com/yindaheng98/ColorAdaptiveGaussianSplatting ACM SIGGRAPH 2026 Daheng Yin Yili Jin Jianxin Shi Isaac Ding Miao Zhang Fangxin Wang Zhaowu Huang Cong Zhang Jiangchuan Liu Fang Dong 10.1145/3799902.3811058 http://arxiv.org/abs/2605.08824v1 2026-05-09T09:19:36Z

Hair is a rich medium of visual and cultural expression, yet its digital modeling remains challenging due to the duality of fluidity and structure. Many existing generative approaches rely primarily on continuous diffusion fields, which entangle global topology with local texture and obscure the semantic and structural organization of hairstyles. To address this, we propose HairGPT, a strand-centric framework that treats strands as generative primitives and formulates realistic 3D hairstyle synthesis as a dual-decoupled autoregressive sequence modeling problem. Our method applies spatial decoupling across semantic scalp regions and structural decoupling along a hierarchical strand representation, progressing from global layout to fine-grained style. We further introduce a geometric tokenizer and region-aware semantic annotations to guide strand-level generation, enabling compositional editing, synthesis of rare and complex hairstyles, and adaptation to stylized domains. By aligning generative modeling with the workflow of digital grooming, HairGPT turns hair generation from opaque texture synthesis into a structured and semantically controllable authoring process, supporting robust semantic conditioning and high-fidelity results across realistic and stylized domains. Project Page: https://haiminluo.github.io/hairgpt/

2026-05-09T09:19:36Z Accepted to SIGGRAPH 2026 (Journal Track) Haimin Luo Min Ouyang Lan Xu Jingyi Yu 10.1145/3811350 http://arxiv.org/abs/2605.06667v1 2026-05-07T17:59:58Z

For artistic applications, video generation requires fine-grained control over both performance and cinematography, i.e., the actor's motion and the camera trajectory. We present ActCam, a zero-shot method for video generation that jointly transfers character motion from a driving video into a new scene and enables per-frame control of intrinsic and extrinsic camera parameters. ActCam builds on any pretrained image-to-video diffusion model that accepts conditioning in terms of scene depth and character pose. Given a source video with a moving character and a target camera motion, ActCam generates pose and depth conditions that remain geometrically consistent across frames. We then run a single sampling process with a two-phase conditioning schedule: early denoising steps condition on both pose and sparse depth to enforce scene structure, after which depth is dropped and pose-only guidance refines high-frequency details without over-constraining the generation. We evaluate ActCam on multiple benchmarks spanning diverse character motions and challenging viewpoint changes. We find that, compared to pose-only control and other pose and camera methods, ActCam improves camera adherence and motion fidelity, and is preferred in human evaluations, especially under large viewpoint changes. Our results highlight that careful camera-consistent conditioning and staged guidance can enable strong joint camera and motion control without training. Project page: https://elkhomar.github.io/actcam/.

2026-05-07T17:59:58Z SIGGRAPH 2026 Omar El Khalifi Thomas Rossi Oscar Fossey Thibault Fouque Ulysse Mizrahi Philip Torr Ivan Laptev Fabio Pizzati Baptiste Bellot-Gurlet http://arxiv.org/abs/2605.06658v1 2026-05-07T17:58:15Z

Recent advances have shown that large-scale video diffusion models can be repurposed as neural renderers by first decomposing videos into intrinsic scene representations and then performing forward rendering under novel illumination. While promising, this paradigm fundamentally relies on accurate intrinsic decomposition, which remains highly unreliable for real-world videos and often leads to distorted appearances, broken materials, and accumulated temporal artifacts during relighting. In this work, we present Relit-LiVE, a novel video relighting framework that produces physically consistent, temporally stable results without requiring prior knowledge of camera pose. Our key insight is to explicitly introduce raw reference images into the rendering process, enabling the model to recover critical scene cues that are inevitably lost or corrupted in intrinsic representations. Furthermore, we propose a novel environment video prediction formulation that simultaneously generates relit videos and per-frame environment maps aligned with each camera viewpoint in a single diffusion process. This joint prediction enforces strong geometric-illumination alignment and naturally supports dynamic lighting and camera motion, significantly improving physical consistency in video relighting while easing the requirement of known per-frame camera pose. Extensive experiments demonstrate that Relit-LiVE consistently outperforms state-of-the-art video relighting and neural rendering methods across synthetic and real-world benchmarks. Beyond relighting, our framework naturally supports a wide range of downstream applications, including scene-level rendering, material editing, object insertion, and streaming video relighting. The Project is available at https://github.com/zhuxing0/Relit-LiVE.

2026-05-07T17:58:15Z Accepted at SIGGRAPH 2026. Project site: https://github.com/zhuxing0/Relit-LiVE Weiqing Xiao Hong Li Xiuyu Yang Houyuan Chen Wenyi Li Tianqi Liu Shaocong Xu Chongjie Ye Hao Zhao Beibei Wang http://arxiv.org/abs/2605.06593v1 2026-05-07T17:20:15Z

Retargeting human kinematic reference motion onto a robot's morphology remains a formidable challenge. Existing methods often produce physical inconsistencies, such as foot sliding, self-collisions, or dynamically infeasible motions, which hinder downstream imitation learning. We propose a bilevel optimization framework that jointly adapts reference motions to a robot's morphology while training a tracking policy using reinforcement learning. To make the optimization tractable, we derive an approximate gradient for the upper-level loss. Our framework requires only a sparse set of semantic rigid-body correspondences and eliminates the need for manual tuning by identifying optimal values for a parameterization expressive enough to preserve characteristic motion across different embodiments. Moreover, by integrating retargeting directly with physics simulation, we produce physically plausible motions that facilitate robust imitation learning. We validate our method in simulation and on hardware, demonstrating challenging motions for morphologies that differ significantly from a human, including retargeting onto a quadruped.

2026-05-07T17:20:15Z SIGGRAPH 2026 David Müller Agon Serifi Sammy Christen Ruben Grandia Espen Knoop Moritz Bächer 10.1145/3811378 http://arxiv.org/abs/2605.05636v1 2026-05-07T03:43:24Z

High-quality facial appearance capture has traditionally required costly studio recording. Recent works consider an in-the-wild smartphone-based setup; however, their model-based inverse rendering paradigm struggles with the complex disentanglement of reflectance from unknown illumination. To bridge this gap, we propose to shift the paradigm into training a powerful delighting network as a prior to constrain the optimization. We leverage the OLAT dataset and the rendered Light Stage scans for training, and propose Dataset Latent Modulation (DLM) to seamlessly integrate these heterogeneous data sources. Specifically, by conditioning the core network on learnable source-aware tokens, we decouple dataset-specific styles from physical delighting principles, enabling the emergence of a delighting prior that outperforms existing proprietary models. This powerful delighting prior enables a simple and automatic appearance capture pipeline that achieves high-quality reflectance estimation from casual video inputs, outperforming prior arts by a large margin. Furthermore, we leverage our appearance capture method to transform the multi-view NeRSemble dataset into NeRSemble-Scan, a large-scale collection of 4K-resolution relightable scans. By open-sourcing our model and the NeRSemble-Scan dataset, we democratize high-end facial capture and provide a new foundation for the research community to build photorealistic digital humans.

2026-05-07T03:43:24Z ACM Transactions on Graphics (Proc. of SIGGRAPH), 2026. Code: https://github.com/yxuhan/OpenDelight Project Page: https://yxuhan.github.io/OpenDelight/index.html Yuxuan Han Xin Ming Tianxiao Li Zhuofan Shen Qixuan Zhang Lan Xu Feng Xu http://arxiv.org/abs/2605.03235v1 2026-05-05T00:00:42Z

Dense random sampling and surfacing of shapes encoded via implicit occupancy functions (OFs) are critical elements of many applications. Existing methods largely provide either one or the other of random sampling or mesh surfaces: ray shooting approaches deliver random samples with no connectivity, and grid-based methods deliver mesh surfaces but their sampling is highly biased. We propose a new method which delivers both pseudo-random OF surface samples and an isosurface mesh connecting them. Our method achieves these goals while requiring an order of magnitude fewer function evaluations than prior approaches. Key to our Adaptive Delaunay Sampling (ADS) approach is a progressively computed Delaunay tetrahedralization of points in 3D space, which we use as a sampling and surfacing scaffold. Starting from an initial coarse Delaunay scaffold, we repeatedly refine crossing edges, ones whose end vertices lie on opposite sides of the surface, augmenting the scaffold with points closer and closer to the surface. Each refinement step uses the Delaunay criterion to incorporate the newly added vertices into the scaffold, introducing new crossing edges. We use the intersections of fine crossing edges with the OF surface as the output samples, and use the marching tetrahedra method to surface these samples. We subsequently use normal estimation to densify the sampling near fine features and in areas of high surface curvature. We validate ADS by sampling 150 inputs at different resolutions, and provide extensive comparisons to existing alternatives. Our experiments demonstrate significant improvement in accuracy/function evaluation count trade-off, and showcase downstream applications.

2026-05-05T00:00:42Z Accepted to SIGGRAPH 2026 Suzuran Takikawa Leo Foord-Kelcey Oliver Oxford Nicholas Vining Alla Sheffer http://arxiv.org/abs/2605.02742v1 2026-05-04T15:41:42Z

Motion in-betweening is one of the most artistically demanding and time consuming stages of 3D animation, where the expressivity and rhythm of motion are defined. The level of creative control it requires makes it a major production bottleneck, underscoring the need for intelligent tools that assist animators in this process. Although recent deep learning approaches have achieved strong results in motion synthesis and in-betweening, they assume data characteristics, motion styles, and problem formulations that diverge from professional animation workflows. To bridge this gap, we propose a method explicitly aligned with the constraints of motion in-betweening for keyframe-based animation in production environments. At its core, the Adaptive Interpolation-Synthesis (AIS) layer mirrors the animator's creative process by dynamically balancing learned interpolation and direct pose synthesis. In addition, a domain-based input keypose schedule reflects the distribution of production data, improving stylistic consistency and alignment between training and real-world usage. Our method achieves state-of-the-art performance on production data; when integrated into Autodesk Maya, it enables animators to complete in-betweening tasks with a 3.5x speedup.

2026-05-04T15:41:42Z Accepted to SIGGRAPH 2026 Conference Papers Anton Raël Julien Boucher Antoine Lhermitte 10.1145/3799902.3811157 http://arxiv.org/abs/2605.00658v1 2026-05-01T13:40:56Z

Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each problem setting, which fixes the input-output mapping and limits the modeling of correlations across modalities. We present UniVidX, a unified multimodal framework that leverages VDM priors for versatile video generation. UniVidX formulates pixel-aligned tasks as conditional generation in a shared multimodal space, adapts to modality-specific distributions while preserving the backbone's native priors, and promotes cross-modal consistency during synthesis. It is built on three key designs. Stochastic Condition Masking (SCM) randomly partitions modalities into clean conditions and noisy targets during training, enabling omni-directional conditional generation instead of fixed mappings. Decoupled Gated LoRA (DGL) introduces per-modality LoRAs that are activated when a modality serves as the generation target, preserving the strong priors of the VDM. Cross-Modal Self-Attention (CMSA) shares keys and values across modalities while keeping modality-specific queries, facilitating information exchange and inter-modal alignment. We instantiate UniVidX in two domains: UniVid-Intrinsic, for RGB videos and intrinsic maps including albedo, irradiance, and normal; and UniVid-Alpha, for blended RGB videos and their constituent RGBA layers. Experiments show that both models achieve performance competitive with state-of-the-art methods across distinct tasks and generalize robustly to in-the-wild scenarios, even when trained on fewer than 1,000 videos. Project page: https://houyuanchen111.github.io/UniVidX.github.io/

2026-05-01T13:40:56Z Project page: https://houyuanchen111.github.io/UniVidX.github.io/ Accepted to ACM Transactions on Graphics (Proceedings of SIGGRAPH 2026) ACM Trans. Graph. 45, 4, Article 51 (July 2026) Houyuan Chen Hong Li Xianghao Kong Tianrui Zhu Shaocong Xu Weiqing Xiao Yuwei Guo Chongjie Ye Lvmin Zhang Hao Zhao Anyi Rao 10.1145/3811304 http://arxiv.org/abs/2605.00548v2 2026-05-10T17:09:06Z

Text-to-image diffusion models generate images by gradually converting white Gaussian noise into a natural image. White Gaussian noise is well suited for producing diverse outputs from a single text prompt due to its absence of structure. However, this very property limits control over, and predictability of, specific visual attributes, as the noise is not human-interpretable. In this work, we investigate the characteristics of the input noise in diffusion models. We show that, although all frequencies in white Gaussian noise have comparable statistical energy, low-frequency components primarily determine the images global structure and color composition, while high-frequency components control finer details. Building on this observation, we demonstrate that simple manipulations of the low-frequency noise using low-frequency image priors can effectively condition the generation process to reconstruct these low-frequency visual cues. This allows us to define a simple, training-free method with minimal overhead that steers overall image structure and color, while letting high-frequency components freely emerge as fine details, enabling variability across generated outputs.

2026-05-01T10:02:14Z SIGGRAPH 2026 Conference Paper. Project Page at: https://nadavc220.github.io/colorful-noise/ Nadav Z. Cohen Ofir Abramovich Ariel Shamir 10.1145/3799902.3811104 http://arxiv.org/abs/2604.28016v1 2026-04-30T15:37:20Z

3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control relies on screen-space positional gradients, which do not distinguish between geometric misplacement and frequency aliasing, often leading to either over-blurred high-frequency textures or inefficient over-densification. We present a structure-aware densification framework. Our key insight is that the decision to subdivide a Gaussian should be driven by an explicit comparison between its projected screen-space extent and the local structure of the texture it seeks to represent. We introduce a multi-scale frequency analysis combining structure tensors with Laplacian scale space analysis to estimate the dominant frequency at each pixel, enabling robust supervision across varying texture scales. Based on this analysis, we define $η$, a per-Gaussian, per-axis frequency violation metric that indicates when a primitive may be under-resolving local texture details. Unlike methods that perform isotropic splitting (e.g., splitting each Gaussian into two smaller ones with uniform shape), our approach performs anisotropic splitting. For each axis with high $η$, we compute a split factor to better resolve the local frequency content. We further introduce a multiview consistency criterion that aggregates $η$ observations across multiple views. By performing densification early and faster, we skip the lengthy iterative densification phases required by baseline methods and achieve significantly faster convergence. Experiments on standard benchmarks demonstrate that our method also achieves superior reconstruction quality, particularly in high-frequency regions.

2026-04-30T15:37:20Z Siggraph 2026 Linjie Lyu Ayush Tewari Jianchun Chen Thomas Leimkühler Christian Theobalt 10.1145/3799902.3811212 http://arxiv.org/abs/2604.27329v1 2026-04-30T02:15:50Z

3D shapes from scanning, reconstruction, or AI-generated content often lack simple quad mesh layouts -- critical for efficient editing and modeling. Existing quad-remeshing techniques typically produce complex layouts with irregular loops, leading to tedious manual cleanup and extensive algorithm tuning. We introduce SQuadGen, a diffusion-based generative framework that leverages Chart Distance Fields (CDF) to synthesize simple quad layouts on 3D shapes. Our approach addresses two key challenges: (1) the discrete nature of mesh connectivity, which hinders learning, and (2) the scarcity of large-scale datasets with simple quad meshes. To overcome the first, we propose CDF, a continuous surface-based representation enabling effective learning and synthesis of quad layouts. To address the second, we define loop-aware simplicity metrics and construct a large-scale dataset of high-quality quad layouts recovered from public 3D repositories through a robust quad-recovery pipeline. Extensive evaluations across diverse 3D inputs show that SQuadGen consistently outperforms existing methods, producing robust, artist-friendly simple quad layouts.

2026-04-30T02:15:50Z SIGGRAPH 2026 (Journal Track), project page: https://youkang-kong.github.io/squadgen/ Youkang Kong Yang Liu Yue Dong Xin Tong Heung-Yeung Shum 10.1145/3811348 http://arxiv.org/abs/2604.26518v1 2026-04-29T10:35:31Z

Lattice metamaterials enable lightweight, multifunctional structures, yet homogenization-based evaluation of their effective properties remains computationally expensive. Neural surrogates offer speed but often lack the accuracy and stability required for engineering-grade simulations. We introduce GMT, a Geometric Multigrid Transformer -- a neural solver with high numerical fidelity for fast and reliable lattice homogenization. GMT achieves architectural alignment with Geometric Multigrid (GMG) by restructuring Point Transformer V3 to operate across sparse GMG hierarchies, capturing long-range dependencies and cross-level interactions essential for multigrid convergence. To enforce physical consistency, GMT incorporates physics-aware positional encoding for strict enforcement of periodicity and predicts both the finest-level solution and multi-level residual corrections. These predictions deliver a spectrally-aligned initialization, enabling end-to-end training under physics-informed and solver-aware losses and requiring only a single GMG V-cycle refinement to reach convergence. This fusion of neural prediction and numerical rigor achieves relative residual errors of $10^{-5}$ with a $160\times$ speedup over state-of-the-art GPU-based solvers at equivalent accuracy -- particularly at high resolutions (e.g. $512^3$), where traditional methods become most costly. We validate GMT across mechanical and thermal domains, demonstrate robust generalization to unseen geometries and non-periodic settings, and showcase scalability to high resolutions -- enabling real-time design iteration, multi-scale simulations, high-throughput material discovery, and inverse design.

2026-04-29T10:35:31Z SIGGRAPH 2026 journal track Yu Xing Yang Liu Tianyang Xue Lin Lu http://arxiv.org/abs/2604.24833v1 2026-04-27T17:58:23Z

Despite transformative advances in generative motion synthesis, real-time interactive motion control remains dominated by traditional techniques. In this work, we identify two key challenges in bridging research and production: 1) Real-time scalability: Industry applications demand real-time generation of a vast repertoire of motion skills, while generative methods exhibit significant degradation in quality and scalability under real-time computation constraints, and 2) Integration: Industry applications demand fine-grained multi-modal control involving velocity commands, style selection, and precise keyframes, a need largely unmet by existing text- or tag-driven models. To overcome these limitations, we introduce MotionBricks: a large-scale, real-time generative framework with a two-fold solution. First, we propose a large-scale modular latent generative backbone tailored for robust real-time motion generation, effectively modeling a dataset of over 350,000 motion clips with a single model. Second, we introduce smart primitives that provide a unified, robust, and intuitive interface for authoring both navigation and object interaction. Applications can be designed in a plug-and-play manner like assembling bricks without expert animation knowledge. Quantitatively, we show that MotionBricks produces state-of-the-art motion quality on open-source and proprietary datasets of various scales, while also achieving a real-time throughput of 15,000 FPS with 2ms latency. We demonstrate the flexibility and robustness of MotionBricks in a complete production-level animation demo, covering navigation and object-scene interaction across various styles with a unified model. To showcase our framework's application beyond animation, we deploy MotionBricks on the Unitree G1 humanoid robot to demonstrate its flexibility and generalization for real-time robotic control.

2026-04-27T17:58:23Z ACM Transactions on Graphics; SIGGRAPH 2026. Project page: https://nvlabs.github.io/motionbricks/ Tingwu Wang Olivier Dionne Michael De Ruyter David Minor Davis Rempe Kaifeng Zhao Mathis Petrovich Ye Yuan Chenran Li Zhengyi Luo Brian Robison Xavier Blackwell Bernardo Antoniazzi Xue Bin Peng Yuke Zhu Simon Yuen http://arxiv.org/abs/2604.23774v2 2026-04-29T12:47:04Z

Text-based 2D image editing models have recently reached an impressive level of maturity, motivating a growing body of work that heavily depends on these models to drive 3D edits. While effective for appearance-based modifications, such 2D-centric 3D editing pipelines often struggle with fine-grained 3D editing, where localized structural changes must be applied while strictly preserving an object's overall identity. To address this limitation, we propose Prox-E, a training-free framework that enables fine-grained 3D control through an explicit, primitive-based geometric abstraction. Our framework first abstracts an input 3D shape into a compact set of geometric primitives. A pretrained vision-language model (VLM) then edits this abstraction to specify primitive-level changes. These structural edits are subsequently used to guide a 3D generative model, enabling fine-grained, localized modifications while preserving unchanged regions of the original shape. Through extensive experiments, we demonstrate that our method consistently balances identity preservation, shape quality, and instruction fidelity more effectively than various existing approaches, including 2D-based 3D editors and training-based methods.

2026-04-26T15:51:57Z Accepted to SIGGRAPH 2026. Project page: https://etaisella.github.io/Prox-E/ Etai Sella Hao Phung Nitay Amiel Or Litany Or Patashnik Hadar Averbuch-Elor http://arxiv.org/abs/2604.23537v1 2026-04-26T05:18:28Z

Rasterization based methods have recently enabled high-quality novel view synthesis at real-time rates, but their underlying volumetric primitives do not expose a direct, globally consistent surface representation, leaving sur face extraction to heuristic post-processing. In contrast, implicit signed dis tance field (SDF) methods provide well-defined surfaces but are typically optimized with computationally expensive ray marching. We propose SD FRaster, a rasterizable SDF representation that bridges this gap by combin ing the efficiency of rasterization with signed distance field for end-to-end mesh reconstruction. Starting from a Delaunay tetrahedralization, we op timize a continuous SDF over a tetrahedral grid and render it efficiently by rasterizing tetrahedra and alpha-compositing their contributions. We further integrate differentiable Marching Tetrahedra into the optimization loop, enablingend-to-endmeshreconstructionwithoutpost-processingmesh extraction. Experiments on DTU and Tanks and Temples demonstrate that SDFRaster achieves higher-quality and more complete surface reconstruc tions with lower storage cost than state-of-the-art approaches. Project page: https://ustc3dv.github.io/SDFRaster/

2026-04-26T05:18:28Z Accepted to SIGGRAPH 2026, Project page: https://ustc3dv.github.io/SDFRaster/ Jinkai Cui Kaiwen Song Chumeng Niu Juyong Zhang http://arxiv.org/abs/2604.22554v1 2026-04-24T13:48:51Z

Transformations produced by image and video generation models often evolve in a highly non-linear manner: long stretches where the content barely changes are followed by sudden, abrupt semantic jumps. To analyze and correct this behavior, we introduce a Semantic Progress Function, a one-dimensional representation that captures how the meaning of a given sequence evolves over time. For each frame, we compute distances between semantic embeddings and fit a smooth curve that reflects the cumulative semantic shift across the sequence. Departures of this curve from a straight line reveal uneven semantic pacing. Building on this insight, we propose a semantic linearization procedure that reparameterizes (or retimes) the sequence so that semantic change unfolds at a constant rate, yielding smoother and more coherent transitions. Beyond linearization, our framework provides a model-agnostic foundation for identifying temporal irregularities, comparing semantic pacing across different generators, and steering both generated and real-world video sequences toward arbitrary target pacing.

2026-04-24T13:48:51Z SIGGRAPH 2026 Gal Metzer Sagi Polaczek Ali Mahdavi-Amiri Raja Giryes Daniel Cohen-Or 10.1145/3799902.3811049 http://arxiv.org/abs/2604.21689v1 2026-04-23T13:55:22Z

Creative face stylization aims to render portraits in diverse visual idioms such as cartoons, sketches, and paintings while retaining recognizable identity. However, current identity encoders, which are typically trained and calibrated on natural photographs, exhibit severe brittleness under stylization. They often mistake changes in texture or color palette for identity drift or fail to detect geometric exaggerations. This reveals the lack of a style-agnostic framework to evaluate and supervise identity consistency across varying styles and strengths. To address this gap, we introduce StyleID, a human perception-aware dataset and evaluation framework for facial identity under stylization. StyleID comprises two datasets: (i) StyleBench-H, a benchmark that captures human same-different verification judgments across diffusion- and flow-matching-based stylization at multiple style strengths, and (ii) StyleBench-S, a supervision set derived from psychometric recognition-strength curves obtained through controlled two-alternative forced-choice (2AFC) experiments. Leveraging StyleBench-S, we fine-tune existing semantic encoders to align their similarity orderings with human perception across styles and strengths. Experiments demonstrate that our calibrated models yield significantly higher correlation with human judgments and enhanced robustness for out-of-domain, artist drawn portraits. All of our datasets, code, and pretrained models are publicly available at https://kwanyun.github.io/StyleID_page/

2026-04-23T13:55:22Z SIGGRAPH 2026 / ACM TOG. Project page at https://kwanyun.github.io/StyleID_page/ Kwan Yun Changmin Lee Ayeong Jeong Youngseo Kim Seungmi Lee Junyong Noh 10.1145/3811360 http://arxiv.org/abs/2604.19039v1 2026-04-21T03:44:13Z

We present a generative method for texture filtering, which exhibits surprisingly good performance and generalizability. Our core idea is to empower texture filtering by taking full advantage of the strong learned image prior of pre-trained generative models. To this end, we propose to fine-tune a pre-trained generative model via a two-stage strategy. Specifically, we first conduct supervised fine-tuning on a very small set of paired images, and then perform reinforcement fine-tuning on a large-scale unlabeled dataset under the guidance of a reward function that quantifies the quality of texture removal and structure preservation. Extensive experiments show that our method clearly outperforms previous methods, and is effective to deal with previously challenging cases. Our code is available at https://github.com/OnlyZZZZ/Generative_Texture_Filtering.

2026-04-21T03:44:13Z Accepted to SIGGRAPH 2026 conference track Rongjia Zheng Shangwei Huang Lei Zhu Wei-Shi Zheng Qing Zhang http://arxiv.org/abs/2604.09132v2 2026-05-02T02:39:12Z

Recent advancements in autoregressive transformers have demonstrated remarkable potential for generating artist-quality meshes. However, the token ordering strategies employed by existing methods typically fail to meet professional artist standards, where coordinate-based sorting yields inefficiently long sequences, and patch-based heuristics disrupt the continuous edge flow and structural regularity essential for high-quality modeling. To address these limitations, we propose Strips as Tokens (SATO), a novel framework with a token ordering strategy inspired by triangle strips. By constructing the sequence as a connected chain of faces that explicitly encodes UV boundaries, our method naturally preserves the organized edge flow and semantic layout characteristic of artist-created meshes. A key advantage of this formulation is its unified representation, enabling the same token sequence to be decoded into either a triangle or quadrilateral mesh. This flexibility facilitates joint training on both data types: large-scale triangle data provides fundamental structural priors, while high-quality quad data enhances the geometric regularity of the outputs. Extensive experiments demonstrate that SATO consistently outperforms prior methods in terms of geometric quality, structural coherence, and UV segmentation. Project page: https://ruixu.me/html/SATO/index.html

2026-04-10T09:13:09Z ACM Transactions on Graphics. SIGGRAPH 2026 Rui Xu Dafei Qin Kaichun Qiao Qiujie Dong Huaijin Pi Qixuan Zhang Longwen Zhang Lan Xu Jingyi Yu Wenping Wang Taku Komura http://arxiv.org/abs/2604.08526v1 2026-04-09T17:57:50Z

Given a person and a garment image, virtual try-on (VTO) aims to synthesize a realistic image of the person wearing the garment, while preserving their original pose and identity. Although recent VTO methods excel at visualizing garment appearance, they largely overlook a crucial aspect of the try-on experience: the accuracy of garment fit -- for example, depicting how an extra-large shirt looks on an extra-small person. A key obstacle is the absence of datasets that provide precise garment and body size information, particularly for "ill-fit" cases, where garments are significantly too large or too small. Consequently, current VTO methods default to generating well-fitted results regardless of the garment or person size. In this paper, we take the first steps towards solving this open problem. We introduce FIT (Fit-Inclusive Try-on), a large-scale VTO dataset comprising over 1.13M try-on image triplets accompanied by precise body and garment measurements. We overcome the challenges of data collection via a scalable synthetic strategy: (1) We programmatically generate 3D garments using GarmentCode and drape them via physics simulation to capture realistic garment fit. (2) We employ a novel re-texturing framework to transform synthetic renderings into photorealistic images while strictly preserving geometry. (3) We introduce person identity preservation into our re-texturing model to generate paired person images (same person, different garments) for supervised training. Finally, we leverage our FIT dataset to train a baseline fit-aware virtual try-on model. Our data and results set the new state-of-the-art for fit-aware virtual try-on, as well as offer a robust benchmark for future research. We will make all data and code publicly available on our project page: https://johannakarras.github.io/FIT.

2026-04-09T17:57:50Z SIGGRAPH 2026 Johanna Karras Yuanhao Wang Yingwei Li Ira Kemelmacher-Shlizerman http://arxiv.org/abs/2603.29924v2 2026-06-18T09:59:27Z

Artistic styles often embed abstraction beyond surface appearance, involving deliberate reinterpretation of structure rather than mere changes in texture or color. Conventional style transfer methods typically preserve the input geometry and therefore struggle to capture this deeper abstraction behavior, especially for illustrative and nonphotorealistic styles. In this work, we introduce Abstraction in Style (AiS), a generative framework that separates structural abstraction from visual stylization. Given a target image and a small set of style exemplars, AiS first derives an intermediate abstraction proxy that reinterprets the target's structure in accordance with the abstraction logic exhibited by the style. The proxy captures semantic structure while relaxing geometric fidelity, enabling subsequent stylization to operate on an abstracted representation rather than the original image. In a second stage, the abstraction proxy is rendered to produce the final stylized output, preserving visual coherence with the reference style. Both stages are implemented using a shared image space analogy, enabling transformations to be learned from visual exemplars without explicit geometric supervision. By decoupling abstraction from appearance and treating abstraction as an explicit, transferable process, AiS supports a wider range of stylistic transformations, improves controllability, and enables more expressive stylization.

2026-03-31T15:59:55Z SIGGRAPH 2026 Min Lu Yuanfeng He Anthony Chen Jianhuang He Pu Wang Daniel Cohen-Or Hui Huang http://arxiv.org/abs/2603.28762v2 2026-06-03T15:05:21Z

Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt. This typicality bias presents a challenge for creative applications that require a wide range of generative outcomes. We identify a fundamental trade-off in current approaches to diversity: modifying model inputs requires costly optimization to incorporate feedback from the generative path. In contrast, acting on spatially-committed intermediate latents tends to disrupt the forming visual structure, leading to artifacts. In this work, we propose to apply repulsion in the Contextual Space as a novel framework for achieving rich diversity in Diffusion Transformers. By intervening in the multimodal attention channels, we apply on-the-fly repulsion during the transformer's forward pass, injecting the intervention between blocks where text conditioning is enriched with emergent image structure. This allows for redirecting the guidance trajectory after it is structurally informed but before the composition is fixed. Our results demonstrate that repulsion in the Contextual Space produces significantly richer diversity without sacrificing visual fidelity or semantic adherence. Furthermore, our method is uniquely efficient, imposing a small computational overhead while remaining effective even in modern "Turbo" and distilled models where traditional trajectory-based interventions typically fail.

2026-03-30T17:59:13Z SIGGRAPH 2026. Project page: https://contextual-repulsion.github.io/ Omer Dahary Benaya Koren Daniel Garibi Daniel Cohen-Or http://arxiv.org/abs/2603.09272v1 2026-03-10T06:57:56Z

Mycorrhizal networks -- often called nature's ``wood-wide web'' -- are vast underground mycelial systems that connect individual plants through countless hyphae of mycorrhizal fungi joining with plant roots. Through these hyphal webs, resources and signals -- carbohydrates, minerals, and biochemical cues -- are mutualistically exchanged and redistributed across plants, sustaining forests as relational symbiotic ecologies rather than isolated individuals. What is it like to be a plant within the wood-wide web? We present \emph{FungiSync}, a multi-person, co-located mixed reality (MR) experience that translates mycorrhizal interdependence into a felt, somaesthetic participatory ritual. Participants embody different forest plants by holding masquerade-style MR headset masks with wood-branch-like handles decorated with mushrooms. In MR, each participant perceives a distinct, audio-reactive psychedelic augmented reality overlay -- composed of resource-representing visual elements -- layered atop a shared physical terrain, symbolizing an individualized digital \emph{umwelt} (perceptual world). FungiSync reprograms human hand touch into a metaphorical mycorrhizal exchange. When participants touch hands, their digital \emph{umwelten} begin to entangle: visual elements leak, mix, and merge across perspectives, as if hyphae were forging new connections and carrying resources between hosts within a larger mycelial network. By making mycorrhizal interdependence perceptible through embodied contact, FungiSync invites participants to feel with \emph{fungal epistemics} -- a more-than-human alternative way of knowing grounded in symbiotic relationality as both an aesthetic experience and an ethical orientation -- offering a critique of the accelerated individualism characterizing our technology-mediated posthuman era.

2026-03-10T06:57:56Z Submitted for SIGGRAPH 2026 Botao Amber Hu Danlin Huang Yilan Elan Tao Xiaobo Aaron Hu Rem RunGu Lin http://arxiv.org/abs/2602.12280v2 2026-05-16T14:13:03Z

Visual illusions traditionally rely on spatial manipulations such as multi-view consistency. In this work, we introduce Progressive Semantic Illusions, a novel vector sketching task where a single sketch undergoes a dramatic semantic transformation through the sequential addition of strokes. We present Stroke of Surprise, a generative framework that optimizes vector strokes to satisfy distinct semantic interpretations at different drawing stages. The core challenge lies in the "dual-constraint": initial prefix strokes must form a coherent object (e.g., a duck) while simultaneously serving as the structural foundation for a second concept (e.g., a sheep) upon adding delta strokes. To address this, we propose a sequence-aware joint optimization framework driven by a dual-branch Score Distillation Sampling (SDS) mechanism. Unlike sequential approaches that freeze the initial state, our method dynamically adjusts prefix strokes to discover a "common structural subspace" valid for both targets. Furthermore, we introduce a novel Overlay Loss that enforces spatial complementarity, ensuring structural integration rather than occlusion. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art baselines in recognizability and illusion strength, successfully expanding visual anagrams from the spatial to the temporal dimension. Project page: https://stroke-of-surprise.github.io/

2026-02-12T18:59:54Z SIGGRAPH 2026. Project page: https://stroke-of-surprise.github.io/ Huai-Hsun Cheng Siang-Ling Zhang Yu-Lun Liu http://arxiv.org/abs/2602.10712v2 2026-05-06T07:08:34Z

We propose a system to optimize parametric designs subject to radiation pressure, \ie the effect of light on the motion of objects. This is most relevant in the design of spacecraft, where radiation pressure presents the dominant non-conservative forcing mechanism, which is the case beyond approximately 800 km altitude. Despite its importance, the high computational cost of high-fidelity radiation pressure modeling has limited its use in large-scale spacecraft design, optimization, and space situational awareness applications. We enable this by offering three innovations in the simulation, in representation and in optimization: First, a practical computer graphics-inspired Monte-Carlo (MC) simulation of radiation pressure. The simulation is highly parallel, uses importance sampling and next-event estimation to reduce variance and allows simulating an entire family of designs instead of a single spacecraft as in previous work. Second, we introduce neural networks as a representation of forces from design parameters. This neural proxy model, learned from simulations, is inherently differentiable and can query forces orders of magnitude faster than a full MC simulation. Third, and finally, we demonstrate optimizing inverse radiation pressure designs, such as finding geometry, material or operation parameters that minimizes travel time, maximizes proximity given a desired end-point, minimize thruster fuel, trains mission control policies or allocated compute budget in extraterrestrial compute.

2026-02-11T10:17:59Z Camera-ready version. Accepted to ACM Transactions on Graphics 45(4). (SIGGRAPH 2026), article 82. 17 pages, 19 figures ACM Transactions on Graphics, Vol. 45, No. 4, Article 82 (July 2026) Charles Constant Elizabeth Bates Santosh Bhattarai Marek Ziebart Tobias Ritschel 10.1145/3811396 http://arxiv.org/abs/2602.09016v3 2026-08-07T03:12:49Z

Reconstructing a structured vector-graphics representation from a rasterized floorplan image is typically an important prerequisite for computational tasks involving floorplans such as automated understanding or CAD workflows. However, existing techniques struggle in faithfully generating the structure and semantics conveyed by complex floorplans that depict large indoor spaces with many rooms and a varying numbers of polygon corners. To this end, we propose Raster2Seq, framing floorplan reconstruction as a sequence-to-sequence task in which floorplan elements--such as rooms, windows, and doors--are represented as labeled polygon sequences that jointly encode geometry and semantics. Our approach introduces an autoregressive decoder that learns to predict the next corner conditioned on image features and previously generated corners using guidance from learnable anchors. These anchors represent spatial coordinates in image space, hence allowing for effectively directing the attention mechanism to focus on informative image regions. By embracing the autoregressive mechanism, our method offers flexibility in the output format, enabling for efficiently handling complex floorplans with numerous rooms and diverse polygon structures. Our method achieves state-of-the-art performance on standard benchmarks such as Structure3D, CubiCasa5K, and Raster2Graph, while also demonstrating strong generalization to more challenging datasets like WAFFLE, which contain diverse room structures and complex geometric variations.

2026-02-09T18:58:46Z Accepted to SIGGRAPH 2026. Project page: https://cornell-vailab.github.io/Raster2Seq/ Hao Phung Hadar Averbuch-Elor http://arxiv.org/abs/2602.05676v2 2026-04-27T11:20:10Z

Recent advancements in 3D foundation models have enabled the generation of high-fidelity assets, yet precise 3D manipulation remains a significant challenge. Existing 3D editing frameworks often face a difficult trade-off between visual controllability, geometric consistency, and scalability. Specifically, optimization-based methods are prohibitively slow, multi-view 2D propagation techniques suffer from visual drift, and training-free latent manipulation methods are inherently bound by frozen priors and cannot directly benefit from scaling. In this work, we present ShapeUP, a scalable, image-conditioned 3D editing framework that formulates editing as a supervised latent-to-latent translation within a native 3D representation. This formulation allows ShapeUP to build on a pretrained 3D foundation model, leveraging its strong generative prior while adapting it to editing through supervised training. In practice, ShapeUP is trained on triplets consisting of a source 3D shape, an edited 2D image, and the corresponding edited 3D shape, and learns a direct mapping using a 3D Diffusion Transformer (DiT). This image-as-prompt approach enables fine-grained visual control over both local and global edits and achieves implicit, mask-free localization, while maintaining strict structural consistency with the original asset. Our extensive evaluations demonstrate that ShapeUP consistently outperforms current trained and training-free baselines in both identity preservation and edit fidelity, offering a robust and scalable paradigm for native 3D content creation.

2026-02-05T13:59:16Z SIGGRAPH 2026. Project page: https://inbar-2344.github.io/ShapeUp-page/ Inbar Gat Dana Cohen-Bar Guy Levy Elad Richardson Daniel Cohen-Or http://arxiv.org/abs/2602.05081v2 2026-07-16T17:08:05Z

Gaussian-based representations have enabled efficient physically-based volume rendering at a fraction of the memory cost of regular, discrete, voxel-based distributions. However, several remaining issues hamper their widespread use. One of the advantages of classic voxel grids is the ease of constructing hierarchical representations by either storing volumetric mipmaps or selectively pruning branches of an already hierarchical voxel grid. Such strategies reduce rendering time and eliminate aliasing when lower levels of detail are required. Constructing similar strategies for Gaussian-based volumes is not trivial. Straightforward solutions, such as prefiltering or computing mipmap-style representations, lead to increased memory requirements or expensive re-fitting of each level separately. Additionally, such solutions do not guarantee a smooth transition between different hierarchy levels. To address these limitations, we propose Gabor Fields, an orientation-selective mixture of Gabor kernels that enables continuous frequency filtering at no cost. The frequency content of the asset is reduced by selectively pruning primitives, directly benefiting rendering performance. Beyond filtering, we demonstrate that stochastically sampling from different frequencies and orientations at each ray recursion enables masking substantial portions of the volume, accelerating ray traversal time in single- and multiple-scattering settings. Furthermore, inspired by procedural volumes, we present an application for efficient design and rendering of procedural clouds as Gabor-noise-modulated Gaussians.

2026-02-04T21:58:03Z Accepted to ACM Transactions on Graphics (SIGGRAPH 2026) ACM Transactions on Graphics 2026, Vol. 45, No. 4, Article 62 Jorge Condor Nicolai Hermann Mehmet Ata Yurtsever Piotr Didyk 10.1145/3811369 http://arxiv.org/abs/2602.04672v4 2026-06-01T04:06:12Z

Reconstructing dynamic hand-object interactions from monocular videos is critical for dexterous manipulation data collection and creating realistic digital twins for robotics and VR. However, current methods face two prohibitive barriers: (1) reliance on neural rendering often yields fragmented, non-simulation-ready geometries under heavy occlusion, and (2) dependence on brittle Structure-from-Motion (SfM) initialization leads to frequent failures on in-the-wild footage. To overcome these limitations, we introduce AGILE, a robust framework that shifts the paradigm from reconstruction to agentic generation for interaction learning. First, we employ an agentic pipeline where a Vision-Language Model (VLM) guides a generative model to synthesize a complete, watertight object mesh with high-fidelity texture, independent of video occlusions. Second, bypassing fragile SfM entirely, we propose a robust anchor-and-track strategy. We initialize the object pose at a single interaction onset frame using a foundation model and propagate it temporally by leveraging the strong visual similarity between our generated asset and video observations. Finally, a contact-aware optimization integrates semantic, geometric, and interaction stability constraints to enforce physical plausibility. Extensive experiments on HO3D, DexYCB, ARCTIC, and in-the-wild videos reveal that AGILE outperforms baselines in global geometric accuracy while demonstrating exceptional robustness on challenging sequences where prior arts frequently collapse. By prioritizing physical validity, our method produces simulation-ready assets validated via real-to-sim retargeting for robotic applications. Project page: https://agile-hoi.github.io.

2026-02-04T15:42:58Z 16 pages, SIGGRAPH 2026 Jin-Chuan Shi Binhong Ye Tao Liu Junzhe He Yangjinhui Xu Xiaoyang Liu Zeju Li Hao Chen Chunhua Shen http://arxiv.org/abs/2602.04349v3 2026-06-25T04:43:09Z

3D editing has emerged as a critical research area to provide users with flexible control over 3D assets. While current editing approaches predominantly focus on 3D Gaussian Splatting or multi-view images, the direct editing of 3D meshes remains underexplored. Prior attempts, such as VoxHammer, rely on voxel-based representations that suffer from limited resolution and necessitate labor-intensive 3D mask. To address these limitations, we propose \textbf{VecSet-Edit}, the first pipeline that leverages the high-fidelity VecSet Large Reconstruction Model (LRM) as a backbone for mesh editing. Our approach is grounded on a analysis of the spatial properties in VecSet tokens, revealing that token subsets govern distinct geometric regions. Based on this insight, we introduce Mask-guided Token Seeding and Attention-aligned Token Gating strategies to precisely localize target regions using only 2D image conditions. Also, considering the difference between VecSet diffusion process versus voxel we design a Drift-aware Token Pruning to reject geometric outliers during the denoising process. Finally, our Detail-preserving Texture Baking module ensures that we not only preserve the geometric details of original mesh but also the textural information. More details can be found in our project page: https://github.com/BlueDyee/VecSet-Edit/tree/main

2026-02-04T09:16:12Z Accepted by SIGGRAPH 2026 Teng-Fang Hsiao Bo-Kai Ruan Yu-Lun Liu Hong-Han Shuai http://arxiv.org/abs/2602.00898v2 2026-06-04T01:26:29Z

We present a fast sparse matrix permutation algorithm tailored to linear systems arising from triangle meshes. Our approach produces nested-dissection-style permutations while significantly reducing permutation runtime overhead. Rather than enforcing strict balance and separator optimality, the algorithm deliberately relaxes these design decisions to favor fast partitioning and efficient elimination-tree construction. Our method decomposes permutation into patch-level local orderings and a compact quotient-graph ordering of separators, preserving the essential structure required by sparse Cholesky factorization while avoiding its most expensive components. We integrate our algorithm into vendor-maintained sparse Cholesky solvers on both CPUs and GPUs. Across a range of graphics applications, including single factorizations and repeated factorizations, our method reduces permutation time and improves the sparse Cholesky solve performance by up to 6.27x. Our code is available at https://github.com/BehroozZare/fast-permute.

2026-01-31T20:56:42Z SIGGRAPH 2026 In Proceedings of the SIGGRAPH 2026 Conference Papers, SIGGRAPH Conference Papers '26, New York, NY, USA, July 2026 Behrooz Zarebavami Ahmed H. Mahmoud Ana Dodik Changcheng Yuan Serban D. Porumbescu John D. Owens Maryam Mehri Dehnavi Justin Solomon 10.1145/3799902.3811189 http://arxiv.org/abs/2601.23065v2 2026-04-30T05:35:29Z

Recent radiance-field-based reconstruction methods, such as NeRF and 3DGS, achieve high visual fidelity for indoor scenes, but often break down under scene editing due to baked illumination and the lack of explicit light transport. In contrast, inverse path tracing methods based on mesh representations enforce correct light transport but require highly accurate geometry, making them difficult to apply robustly to real indoor scenes. We present Emission-Aware Gaussians and Path Tracing (EAG-PT), a method for physically based reconstruction and rendering of indoor scenes using a unified 2D Gaussian representation, targeting editable diffuse global illumination. Our approach consists of three key ideas: (1) representing indoor scenes with 2D Gaussians as a transport-friendly geometric proxy that avoids explicit mesh reconstruction; (2) explicitly separating emissive and non-emissive components during reconstruction to support editing; and (3) decoupling reconstruction from final rendering by using efficient single-bounce optimization and high-quality multi-bounce path tracing, respectively. Experiments on synthetic and real indoor scenes show that EAG-PT produces more natural and physically consistent edited renderings than radiance-field reconstructions, while preserving finer geometric detail and avoiding mesh-induced artifacts compared with mesh-based inverse path tracing. These results highlight the potential of our approach for applications such as interior design, XR content creation, and embodied AI.

2026-01-30T15:16:37Z SIGGRAPH 2026 Conference Paper; Project Page: https://eag-pt.github.io Xijie Yang Mulin Yu Changjian Jiang Kerui Ren Tao Lu Jiangmiao Pang Dahua Lin Bo Dai Linning Xu 10.1145/3799902.3811054 http://arxiv.org/abs/2601.21141v1 2026-01-29T00:50:03Z

This paper presents AnthropoCam, a mobile-based neural style transfer (NST) system optimized for the visual synthesis of Anthropocene environments. Unlike conventional artistic NST, which prioritizes painterly abstraction, stylizing human-altered landscapes demands a careful balance between amplifying material textures and preserving semantic legibility. Industrial infrastructures, waste accumulations, and modified ecosystems contain dense, repetitive patterns that are visually expressive yet highly susceptible to semantic erosion under aggressive style transfer. To address this challenge, we systematically investigate the impact of NST parameter configurations on the visual translation of Anthropocene textures, including feature layer selection, style and content loss weighting, training stability, and output resolution. Through controlled experiments, we identify an optimal parameter manifold that maximizes stylistic expression while preventing semantic erasure. Our results demonstrate that appropriate combinations of convolutional depth, loss ratios, and resolution scaling enable the faithful transformation of anthropogenic material properties into a coherent visual language. Building on these findings, we implement a low-latency, feed-forward NST pipeline deployed on mobile devices. The system integrates a React Native frontend with a Flask-based GPU backend, achieving high-resolution inference within 3-5 seconds on general mobile hardware. This enables real-time, in-situ visual intervention at the site of image capture, supporting participatory engagement with Anthropocene landscapes. By coupling domain-specific NST optimization with mobile deployment, AnthropoCam reframes neural style transfer as a practical and expressive tool for real-time environmental visualization in the Anthropocene.

2026-01-29T00:50:03Z 7 pages, 11 figures, submitted to SIGGRAPH 2026 Po-Hsun Chen Ivan C. H. Liu http://arxiv.org/abs/2601.19843v3 2026-06-09T10:18:44Z

We propose a new framework to systematically incorporate data uncertainty in Gaussian Splatting. Being the new paradigm of neural rendering, Gaussian Splatting has been investigated in many applications, with the main effort in extending its representation, improving its optimization process, and accelerating its speed. However, one orthogonal, much needed, but under-explored area is data uncertainty. In standard 4D Gaussian Splatting, data uncertainty can manifest as view sparsity, missing frames, camera asynchronization, etc. So far, there has been little research to holistically incorporating various types of data uncertainty under a single framework. To this end, we propose Graphical X Splatting, or GraphiXS, a new probabilistic framework that considers multiple types of data uncertainty, aiming for a fundamental augmentation of the current 4D Gaussian Splatting paradigm into a probabilistic setting. GraphiXS is general and can be instantiated with a range of primitives, e.g. Gaussians, Student's-t. Furthermore, GraphiXS can be used to `upgrade' existing methods to accommodate data uncertainty. Through exhaustive evaluation and comparison, we demonstrate that GraphiXS can systematically model various uncertainties in data, outperform existing methods in many settings where data are missing or polluted in space and time, and therefore is a major generalization of the current 4D Gaussian Splatting research.

2026-01-27T17:50:07Z Accepted to SIGGRAPH 2026 Doğa Yılmaz Jialin Zhu Deshan Gong He Wang 10.1145/3799902.3811085 http://arxiv.org/abs/2601.17740v2 2026-04-15T09:00:14Z

Sewing patterns define the structural foundation of garments and are essential for applications such as fashion design, fabrication, and physical simulation. Despite progress in automated pattern generation, accurately modeling sewing patterns remains difficult due to the broad variability in panel geometry and seam arrangements. In this work, we introduce a sewing pattern modeling method based on an implicit representation. We represent each panel using a signed distance field that defines its boundary and an unsigned distance field that identifies seam endpoints, and encode these fields into a continuous latent space that enables differentiable meshing. A latent flow matching model learns distributions over panel combinations in this representation, and a stitching prediction module recovers seam relations from extracted edge segments. This formulation allows accurate modeling and generation of sewing patterns with complex structures. We further show that it can be used to estimate sewing patterns from images with improved accuracy relative to existing approaches, and supports applications such as pattern completion and refitting, providing a practical tool for digital fashion design.

2026-01-25T08:18:39Z SIGGRAPH 2026 Cong Cao Ren Li Corentin Dumery Hao Li http://arxiv.org/abs/2601.17361v1 2026-01-24T08:14:08Z

Cellular automata (CA), originally developed as computational models of natural processes, have become a central subject in the study of complex systems and generative visual forms. Among them, the Ulam-Warburton Cellular Automaton (UWCA) exhibits recursive growth and fractal-like characteristics in its spatial evolution. However, exact self-similar fractal structures are typically observable only at specific generations and remain visually obscured in conventional binary renderings. This study introduces a Recursive Gradient Profile Function (RGPF) that assigns grayscale values to newly activated cells according to their generation index, enabling latent self-similar structures to emerge cumulatively in spatial visualizations. Through this gradient-based mapping, recursive geometric patterns become perceptible across scales, revealing fractal properties that are not apparent in standard representations. We further extend this approach to UWCA variants with alternative neighborhood configurations, demonstrating that these rules also produce distinct yet consistently fractal visual patterns when visualized using recursive gradient profile. Beyond computational analysis, the resulting generative forms resonate with optical and cultural phenomena such as infinity mirrors, video feedback, and mise en abyme in European art history, as well as fractal motifs found in religious architecture. These visual correspondences suggest a broader connection between complexity science, computational visualization, and cultural art and design.

2026-01-24T08:14:08Z 8 pages, 10 figures, submitted to SIGGRAPH 2026 Chung-En Hao Ivan C. H. Liu http://arxiv.org/abs/2601.05127v2 2026-04-23T07:24:19Z

Recent diffusion-based image editing methods commonly rely on text or high-level instructions to guide the generation process, offering intuitive but coarse control. In contrast, we focus on explicit, prompt-free editing, where the user directly specifies the modification by cropping and pasting an object or sub-object into a chosen location within an image. This operation affords precise spatial and visual control, yet it introduces a fundamental challenge: preserving the identity of the pasted object while harmonizing it with its new context. We observe that attention maps in diffusion-based editing models inherently govern whether image regions are preserved or adapted for coherence. Building on this insight, we introduce LooseRoPE, a saliency-guided modulation of rotational positional encoding (RoPE) that loosens the positional constraints to continuously control the attention field of view. By relaxing RoPE in this manner, our method smoothly steers the model's focus between faithful preservation of the input image and coherent harmonization of the inserted object, enabling a balanced trade-off between identity retention and contextual blending. Our approach provides a flexible and intuitive framework for image editing, achieving seamless compositional results without textual descriptions or complex user input.

2026-01-08T17:17:47Z Accepted to SIGGRAPH 2026. Project Page: https://snap-research.github.io/LooseRoPE/ Etai Sella Yoav Baron Hadar Averbuch-Elor Daniel Cohen-Or Or Patashnik http://arxiv.org/abs/2512.18181v3 2026-05-07T04:12:26Z

With the rise of online dance-video platforms and rapid advances in AI-generated content (AIGC), music-driven dance generation has emerged as a compelling research direction. Despite substantial progress in related domains such as music-driven 3D dance generation, pose-driven image animation, and audio-driven talking-head synthesis, existing methods cannot be directly adapted to this task. Moreover, the limited studies in this area still struggle to jointly achieve high-quality visual appearance and realistic human motion. Accordingly, we present MACE-Dance, a music-driven dance video generation framework with cascaded Mixture-of-Experts (MoE). The Motion Expert performs music-to-3D motion generation while enforcing kinematic plausibility and artistic expressiveness, whereas the Appearance Expert carries out motion- and reference-conditioned video synthesis, preserving visual identity with spatiotemporal coherence. Specifically, the Motion Expert adopts a diffusion model with a BiMamba-Transformer hybrid architecture and a Guidance-Free Training (GFT) strategy, achieving state-of-the-art (SOTA) performance in 3D dance generation. The Appearance Expert employs a decoupled kinematic-aesthetic fine-tuning strategy, achieving state-of-the-art (SOTA) performance in pose-driven image animation. To better benchmark this task, we curate a large-scale and diverse dataset and design a motion-appearance evaluation protocol. Based on this protocol, MACE-Dance also achieves state-of-the-art performance. Code is available at https://github.com/AMAP-ML/MACE-Dance.

2025-12-20T02:34:34Z Accepted by SIGGRAPH 2026 Kaixing Yang Jiashu Zhu Xulong Tang Ziqiao Peng Xiangyue Zhang Puwei Wang Jiahong Wu Xiangxiang Chu Hongyan Liu Jun He http://arxiv.org/abs/2512.12151v3 2026-05-28T17:21:03Z

We introduce a barrier-free optimization framework for non-penetration elastodynamic simulation that matches the robustness of Incremental Potential Contact (IPC) while overcoming its two primary efficiency bottlenecks: (1) reliance on logarithmic barrier functions to enforce non-penetration constraints, which leads to ill-conditioned systems and significantly slows down the convergence of iterative linear solvers; and (2) the time-of-impact (TOI) locking issue, which restricts active-set exploration in collision-intensive scenes and requires a large number of Newton iterations. We propose a novel second-order constrained optimization framework featuring a custom augmented Lagrangian solver that avoids TOI locking by immediately incorporating all requisite contact pairs detected via CCD, enabling more efficient active-set exploration and leading to significantly fewer Newton iterations. By adaptively updating Lagrange multipliers rather than increasing penalty stiffness, our method prevents stagnation at zero TOI while maintaining a well-conditioned system. We further introduce a constraint filtering and decay mechanism to keep the active set compact and stable, along with a theoretical justification of our method's finite-step termination and first-order time integration accuracy under a cumulative TOI-based termination criterion. A comprehensive set of experiments demonstrates the efficiency, robustness, and accuracy of our method. With a GPU-optimized simulator design, our method achieves an up to 103x speedup over GIPC on challenging, contact-rich benchmarks - scenarios that were previously tractable only with barrier-based methods. Our code and data are open-sourced at https://simulation-intelligence.github.io/barrier-free .

2025-12-13T03:17:12Z ACM Transactions on Graphics, 2026 (presentation at SIGGRAPH 2026) Juntian Zheng Zhaofeng Luo Minchen Li 10.1145/3811035 http://arxiv.org/abs/2512.03028v3 2026-04-24T21:34:07Z

Data-driven motion priors that can guide agents toward producing naturalistic behaviors play a pivotal role in creating life-like virtual characters. Adversarial imitation learning has been a highly effective method for learning motion priors from reference motion data. However, adversarial priors, with few exceptions, need to be retrained for each new controller, thereby limiting their reusability and necessitating the retention of the reference motion data when applied to downstream tasks. In this work, we present Score-Matching Motion Priors (SMP), which leverages pre-trained motion diffusion models and score distillation sampling (SDS) to create reusable task-agnostic motion priors. SMPs can be pre-trained on a motion dataset, independent of any control policy or task. Once trained, SMPs can be kept frozen and reused as general-purpose reward functions to train new policies to produce naturalistic behaviors for downstream tasks. We show that a general motion prior trained on large-scale datasets can be repurposed into a variety of style-specific priors. Furthermore, SMP can compose different styles to synthesize new styles not present in the original dataset. Our method can create reusable and modular motion priors that produce high-quality motions comparable to state-of-the-art adversarial imitation learning methods. In our experiments, we demonstrate the effectiveness of SMP across a diverse suite of control tasks with physically simulated humanoid characters. Video available at https://youtu.be/jBA2tWk6vzU

2025-12-02T18:54:12Z To appear in ACM Transactions on Graphics (SIGGRAPH 2026) Yuxuan Mu Ziyu Zhang Yi Shi Dun Yang Minami Matsumoto Kotaro Imamura Guy Tevet Chuan Guo Michael Taylor Chang Shu Pengcheng Xi Xue Bin Peng http://arxiv.org/abs/2510.18189v2 2026-06-12T22:56:08Z

Global illumination (GI) is essential for realistic rendering but remains computationally expensive due to the complexity of simulating indirect light transport. Recent neural methods have mainly relied on per-scene optimization, sometimes extended to handle changes in camera or geometry. Efforts toward cross-scene generalization have largely stayed in 2D screen space, such as neural denoising or G-buffer based GI prediction, which often suffer from view inconsistency and limited spatial understanding. We propose a generalizable 3D light transport embedding that approximates global illumination directly from 3D scene configurations, without using rasterized or path-traced cues. Each scene is represented as a point cloud with geometric and material features. A scalable transformer models global point-to-point interactions to encode these features into neural primitives. At render time, each query point retrieves nearby primitives via nearest-neighbor search and aggregates their latent features through cross-attention to predict the desired rendering quantity. We demonstrate results on diffuse global illumination prediction across diverse indoor scenes with varying layouts, geometry, and materials. The embedding trained for irradiance estimation can be quickly adapted to new rendering tasks with limited fine-tuning. We also present preliminary results for spatial-directional radiance field estimation for glossy materials and show how the normalized field can accelerate unbiased path guiding. This approach highlights a path toward integrating learned priors into rendering pipelines without explicit ray-traced illumination cues.

2025-10-21T00:29:09Z SIGGRAPH 2026 Bing Xu Mukund Varma T Cheng Wang Tzu-Mao Li Lifan Wu Bartlomiej Wronski Ravi Ramamoorthi Marco Salvi 10.1145/3799902.3811095 http://arxiv.org/abs/2509.00406v3 2026-06-04T01:12:40Z

We present a GPU-based system for automatic differentiation (AD) of functions defined on triangle meshes, designed to exploit the locality and sparsity in mesh-based computation. Our system evaluates derivatives using per-element forward-mode AD, confining all computation to registers and shared memory and assembling global gradients, sparse Jacobians, and sparse Hessians directly on the GPU. By avoiding global computation graphs, intermediate buffers, and device-host synchronization, our approach minimizes memory traffic and enables efficient differentiation under both static and dynamically changing sparsity. Our programming model lets users express energy terms over mesh neighborhoods, while our system automatically manages parallel execution, derivative propagation, sparse assembly, and matrix-free operations such as Hessian-vector products. Our system supports both scalar- and vector-valued objectives, dynamic interaction-driven sparsity updates, and seamless integration with external GPU sparse linear solvers. We evaluate our system on applications including elastic and cloth simulation, surface parameterization, mesh smoothing, frame field design, ARAP deformation, and spherical manifold optimization. Across these tasks, our system consistently outperforms state-of-the-art differentiation frameworks, including PyTorch, JAX, Warp, DrJIT, EnzymeAD, and Thallo. We demonstrate speedups across a range of solver types, from Newton and Gauss-Newton for nonlinear least squares to L-BFGS and gradient descent, and across different derivative usage modes, including Hessian-vector products as well as full sparse Hessian and Jacobian construction. Our system is available as open source at https://github.com/owensgroup/RXMesh.

2025-08-30T08:30:48Z SIGGRAPH 2026 ACM Transactions on Graphics, 45(4), July 2026 Ahmed H. Mahmoud Rahul Goel Jonathan Ragan-Kelley Justin Solomon 10.1145/3811338 http://arxiv.org/abs/2508.10201v4 2026-07-18T10:35:55Z

Computer-Aided Design (CAD) models, given their compactness and precision, remain the industry standard for designing and fabricating engineering objects. However, language-guided CAD editing is still in its infancy, largely due to missing semantic connection between user commands and underlying shape geometry, a problem exacerbated by the shortage of paired text-and-edit CAD datasets. While recent Multimodal Large Language Models (mLLMs) have attempted to bridge this gap, their reliance on CAD construction history -- often an expensive and hard to obtain input -- severely limits their expressiveness and restricts their usage. We present B-repLer, a novel framework that directly connects natural language with editing CAD models by operating in a learned latent space. Importantly, our approach bypasses the need for construction history, enabling semantic edits on a wide range of geometries, from simple prismatic parts to complex freeform shapes defined by B-Spline surfaces. To facilitate this research, we introduce BrepEDIT-240K, the first large-scale dataset for this task. We demonstrate how this paired dataset can be automatically generated, (user) validated, and scaled by leveraging existing CAD tools, in conjunction with mLLMs, to create the required paired data without relying on any external annotations. Our results demonstrate that B-repLer can accurately perform complex edits on complex CAD shapes, even when the input edit specifications are high-level and ambiguous to interpret, consistently producing valid, high-quality CAD outputs enabling a class of text-guided edits not previously possible.

2025-08-13T21:23:56Z Accepted by SIGGRAPH 2026; Project page at https://yilinliu77.github.io/brepler.github.io Code at https://github.com/yilinliu77/Brepler Yilin Liu Niladri Shekhar Dutt Changjian Li Niloy J. Mitra http://arxiv.org/abs/2405.13729v3 2026-04-29T09:10:05Z

In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, additional attributes are combined to associate with data samples. We show that the space spanned by the combination of dimensions and attributes can be insufficiently covered by existing training schemes of diffusion generative models, potentially limiting test time performance. We present a simple fix to this problem by constructing stochastic processes that fully exploit the combinatorial structures, hence the name ComboStoc. Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes. Moreover, ComboStoc enables a new way of test time generation which uses asynchronous time steps for different dimensions and attributes, thus allowing for varying degrees of control over them. Our code is available at: https://github.com/Xrvitd/ComboStoc

2024-05-22T15:23:10Z ACM Transactions on Graphics, SIGGRAPH 2026 Rui Xu Jiepeng Wang Hao Pan Yang Liu Xin Tong Shiqing Xin Changhe Tu Taku Komura Wenping Wang