ACM Transactions on Graphics最新文献

Robust and Efficient Penetration-Free Elastodynamics without Barriers 鲁棒和高效无穿透弹性动力学无障碍

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-04-20 DOI: 10.1145/3811035

Juntian Zheng, Zhaofeng Luo, Minchen Li

{"title":"Robust and Efficient Penetration-Free Elastodynamics without Barriers","authors":"Juntian Zheng, Zhaofeng Luo, Minchen Li","doi":"10.1145/3811035","DOIUrl":"https://doi.org/10.1145/3811035","url":null,"abstract":"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. A comprehensive set of experiments demonstrates the efficiency, robustness, finite-step termination, and first-order time integration accuracy of our method under a cumulative TOI-based termination criterion. With a GPU-optimized simulator design, our method achieves an up to 103 × 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.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"93 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147720040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Guidestar-Free Adaptive Optics with Asymmetric Apertures 非对称孔径无导星自适应光学

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-04-17 DOI: 10.1145/3809501

Weiyun Jiang, Haiyun Guo, Christopher A. Metzler, Ashok Veeraraghavan

{"title":"Guidestar-Free Adaptive Optics with Asymmetric Apertures","authors":"Weiyun Jiang, Haiyun Guo, Christopher A. Metzler, Ashok Veeraraghavan","doi":"10.1145/3809501","DOIUrl":"https://doi.org/10.1145/3809501","url":null,"abstract":"This work introduces the first closed-loop adaptive optics (AO) system capable of optically correcting aberrations in real-time without a guidestar or a wavefront sensor. Nearly 40 years ago, Cederquist et al. demonstrated that asymmetric apertures enable phase retrieval (PR) algorithms to perform fully computational wavefront sensing, albeit at a high computational cost. More recently, Chimitt et al. extended this approach with machine learning and demonstrated real-time wavefront sensing using only a single (guidestar-based) point-spread-function (PSF) measurement. Inspired by these works, we introduce a guidestar-free AO framework built around asymmetric apertures and machine learning. Our approach combines three key elements: (1) an asymmetric aperture placed at the system’s pupil plane that enables PR-based wavefront sensing, (2) a pair of machine learning algorithms that estimate the PSF from natural scene measurements and reconstruct phase aberrations, and (3) a spatial light modulator that performs optical correction. We experimentally validate this framework on dense natural scenes imaged through unknown obscurants. Our method outperforms state-of-the-art guidestar-free wavefront shaping methods, using an order of magnitude fewer measurements and three orders of magnitude less computation.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"85 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147695308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Tensor Decomposition-Based Four-dimensional Background-Oriented Schlieren Tomography for High-Speed, High-Fidelity Flow Field Reconstruction 基于张量分解的四维背景纹影层析成像高速高保真流场重建

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-04-15 DOI: 10.1145/3809488

Yuanzhe He, Yutao Zheng, Shijie Xu, Ning Liu, Yingzheng Liu, Weiwei Cai

{"title":"Tensor Decomposition-Based Four-dimensional Background-Oriented Schlieren Tomography for High-Speed, High-Fidelity Flow Field Reconstruction","authors":"Yuanzhe He, Yutao Zheng, Shijie Xu, Ning Liu, Yingzheng Liu, Weiwei Cai","doi":"10.1145/3809488","DOIUrl":"https://doi.org/10.1145/3809488","url":null,"abstract":"This work introduces an efficient reconstruction algorithm for time-resolved background-oriented Schlieren tomography (BOST) by leveraging tensor decomposition and neural networks. The proposed algorithm organizes data into a four-dimensional spatiotemporal tensor (X-Y-Z-T) and applies a decomposition strategy based on three component sets: (XY-ZT), (XZ-YT), and (YZ-XT). To enhance efficiency and accuracy, tensor decomposition is integrated with a lightweight neural network. Additionally, a specialized distortion correction model is designed to address light ray path distortions caused by inhomogeneous dynamic flow fields. This network iteratively corrects light ray displacements at the background plate, ensuring precise compensation for distortions. The framework employs an integrated optimization strategy, performing bilinear-interpolated ray tracing followed by back-propagation to update tensor factorization components and neural network parameters. Mixed-precision computations are utilized to accelerate convergence, with single-precision operations for the forward process and half-precision for back-propagation. Experimental results demonstrate that the proposed method significantly reduces memory usage and reconstruction time while improving accuracy. Notably, it achieves a processing time of 12.6 seconds per frame without pre-training, with potential for further acceleration. This work provides a novel and streamlined approach for time-resolved visualization of complex flow fields, offering promising applications in fluid dynamics and combustion physics.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"156 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147681571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

OmniHands: Robust Motion Capture of Interactive Hands via A Versatile Transformer OmniHands：通过多功能变压器的交互式手的鲁棒运动捕捉

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-04-11 DOI: 10.1145/3807943

Dixuan Lin, Yuxiang Zhang, Mengcheng Li, Wei Jing, Qi Yan, Qianying Wang, Yebin Liu, Hongwen Zhang

{"title":"OmniHands: Robust Motion Capture of Interactive Hands via A Versatile Transformer","authors":"Dixuan Lin, Yuxiang Zhang, Mengcheng Li, Wei Jing, Qi Yan, Qianying Wang, Yebin Liu, Hongwen Zhang","doi":"10.1145/3807943","DOIUrl":"https://doi.org/10.1145/3807943","url":null,"abstract":"In this paper, we introduce OmniHands, a universal approach to recovering interactive hand motions and their relative movement from monocular or multi-view inputs. Our approach addresses three major limitations of previous methods: lacking a unified solution for handling single hand and interactive hands image inputs, lacking a versatile framework to support various 4D tasks such as video-based tasks and multi-view tasks, and unable to maintain robust performance in real-world data. To overcome these challenges, we develop a universal architecture with novel tokenization and contextual feature fusion strategies, capable of adapting to a variety of tasks. Specifically, we propose a Relation-aware Two-Hand Tokenization (RAT) method to embed positional relation information into the hand tokens. In this way, our network can handle both single-hand and two-hand inputs and explicitly leverage relative hand positions, facilitating the reconstruction of intricate hand interactions in real-world scenarios. As such tokenization indicates the relative relationship of two hands, it also supports more effective feature fusion. To this end, we further develop a 4D Interaction Reasoning (FIR) module to fuse hand tokens in 4D with attention and decode them into 3D hand meshes and relative temporal movements. The efficacy of our approach is validated on several benchmark datasets. The results on in-the-wild videos and real-world scenarios demonstrate the superior performances of our approach for interactive hand reconstruction. The code and video results can be found in the supplementary materials.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"20 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147648995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Loops2Roofs: Diffusion-based 3D Roof Generation using a Loop Representation Loops2Roofs：使用循环表示的基于扩散的3D屋顶生成

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-04-10 DOI: 10.1145/3807955

Jianwei Guo, Pu Li, Qi Zeng, Wenhao Zhang, Pengxu Li, Liangliang Nan, Bedrich Benes, Dongming Yan

{"title":"Loops2Roofs: Diffusion-based 3D Roof Generation using a Loop Representation","authors":"Jianwei Guo, Pu Li, Qi Zeng, Wenhao Zhang, Pengxu Li, Liangliang Nan, Bedrich Benes, Dongming Yan","doi":"10.1145/3807955","DOIUrl":"https://doi.org/10.1145/3807955","url":null,"abstract":"Effectively representing and generating 3D roof structures remains a challenging task in urban modeling. This paper introduces a loop-based roof representation (LFR) and Loops2Roofs algorithm, a novel diffusion-based generative approach that directly outputs 3D polygonal roof meshes using the LFR. Our key novelty lies in representing the roofs as a set of polygonal faces bounded by loops. This flexible representation improves generalization to complex roof structures across different architectural styles and can be effectively learned and generated by machine learning models. Roof generation proceeds in two stages. First, a Transformer-based diffusion model directly denoises the 3D coordinates of roof face vertices. This model is conditioned on structural priors, specifically the number of roof faces and vertices per face, which are pre-generated using an auto-regressive model. Second, a neural stitching module enforces roof topology and recovers the geometric incident relationships between edges of different 3D loops. Optionally, our algorithm can incorporate 2D building footprints as input for image-conditioned roof generation. The final output is a compact, structured roof mesh encoded in the LFR format. We demonstrate the effectiveness and efficiency of our approach by generating diverse, realistic roof models, ranging from synthetic to real-world buildings. Experiments show that Loops2Roofs significantly advances structured roof generation, outperforming existing methods on three benchmarks.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"20 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147641522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Robust and Efficient Intersection Algorithm for NURBS Surfaces: Handling Small Loops and Tangent Intersections NURBS曲面的鲁棒高效交点算法：处理小环和切线交点

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-04-10 DOI: 10.1145/3807948

Jieyin Yang, Xiaohong Jia

{"title":"A Robust and Efficient Intersection Algorithm for NURBS Surfaces: Handling Small Loops and Tangent Intersections","authors":"Jieyin Yang, Xiaohong Jia","doi":"10.1145/3807948","DOIUrl":"https://doi.org/10.1145/3807948","url":null,"abstract":"Computing the intersection curve of NURBS surfaces is a fundamental task in modern Computer-Aided Design (CAD) systems. The topological correctness of intersection algorithms has a significant impact on the reliability of a CAD system. Despite decades of evolution in the industrial community, efficiently identifying all intersection branches remains challenging, particularly in scenarios involving complex intersection topology with small loops or degenerate cases. In this paper, we propose a novel approach to effectively detect all intersection branches by computing their starting points robustly. The proposed method combines the principles of winding number theory with a subdivision scheme for the vector field on the parametric domain of one input surface. The use of winding number theory facilitates the detection of small loops or isolated singularities, while the subdivision scheme ensures the accurate localization of starting points on tangential intersection branches within these curves. We demonstrate the effectiveness of our method in detecting starting points across various common and complex intersection topology, outperforming both commercial and open-source geometric kernels in terms of topological correctness and computation speed when handling small loops and degenerate situations.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"99 2 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147641464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Precision Controlled Surface-Surface Intersection Algorithm for NURBS NURBS的一种精密控制曲面相交算法

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-04-09 DOI: 10.1145/3806045

Gangyi Li, Xi Wu, Zhongxuan Luo, Lei Na, Jin-San Cheng

引用次数: 0

Fast and Accurate Gaussian Process Modelling of Real-World Materials 快速和准确的高斯过程建模的真实世界的材料

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-03-31 DOI: 10.1145/3806194

Arnau Colom, Christian Bouville, Julien Pettre, Kadi Bouatouch, Ricardo Marques

{"title":"Fast and Accurate Gaussian Process Modelling of Real-World Materials","authors":"Arnau Colom, Christian Bouville, Julien Pettre, Kadi Bouatouch, Ricardo Marques","doi":"10.1145/3806194","DOIUrl":"https://doi.org/10.1145/3806194","url":null,"abstract":"Our goal in this paper is to propose a fast and easy to implement BRDF modeling method that provides both accurate and compact representations for all types of BRDF, i.e., isotropic or anisotropic. To achieve this objective, we use a Bayesian regression method with a Gaussian process prior which allows obtaining compact BRDF representations in a purely analytical way. For this purpose, we use a generalized covariance kernel which is much better suited to BRDF features than the usual Gaussian kernel. To speed up the processing, we adapt this method to the specificities of BRDFs through an appropriate input data structure and distribution of observations so as to drastically reduce the problem dimensionality through an efficient factorization method. In this way, all calculations at both fitting and rendering steps are reduced to basic matrix products and the computation of a BRDF representation with our modeling method takes only a few seconds. Furthermore, rather than using a systematic approach as in state-of-the-art methods, the size and complexity of the BRDF representation can be adapted to the application requirements as regards the fitting accuracy and rendering constraints. Besides, our BRDF representation can be easily converted to spherical harmonics expansions, which allows easier integration in usual rendering algorithms. We also propose importance sampling methods derived from our BRDF modeling method that leads to fast and easy implementations. Experimental applications of our method to various types of isotropic and anisotropic BRDFs show that state-of-the-art methods can be outperformed in most cases by using a small set of observations for the regression.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"192 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147586437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Simple-RF: Regularizing Sparse Input Radiance Fields with Simpler Solutions Simple-RF：用更简单的解决方案正则化稀疏输入辐射场

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-03-28 DOI: 10.1145/3806041

Nagabhushan Somraj, Sai Harsha Mupparaju, Adithyan Karanayil, Rajiv Soundararajan

{"title":"Simple-RF: Regularizing Sparse Input Radiance Fields with Simpler Solutions","authors":"Nagabhushan Somraj, Sai Harsha Mupparaju, Adithyan Karanayil, Rajiv Soundararajan","doi":"10.1145/3806041","DOIUrl":"https://doi.org/10.1145/3806041","url":null,"abstract":"Neural Radiance Fields (NeRF) show impressive performances in photo-realistic free-view rendering of scenes. Recent improvements such as TensoRF and ZipNeRF employ explicit models for faster optimization and rendering. However, all these radiance fields require a dense sampling of images in the given scene for effective training. Their performances degrade significantly when only a sparse set of views is available. Existing depth priors used to supervise the radiance fields are either sparse or suffer from generalization issues. We seek to learn scene-specific dense depth priors to regularize the radiance fields. Further, we desire a framework of regularizations that can work across different radiance field models. We observe that certain features of the radiance fields, such as positional encoding, number of decomposed tensor components or size of the hash table, cause overfitting in the sparse-input scenario. We design augmented models by reducing the capacity of these features and train them along with the main radiance field. These augmented models learn simpler solutions, which estimate better depth in certain regions. By supervising the main radiance field with such depths, we significantly improve the performance of the radiance fields on popular forward-facing and 360° datasets by employing the above regularization.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"108 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147535830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Complex-Valued Holographic Radiance Fields 复值全息辐射场

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-03-24 DOI: 10.1145/3804450

Yicheng Zhan, Dong-Ha Shin, Seung-Hwan Baek, Kaan Akşit

引用次数: 0