ACM Transactions on Graphics最新文献_第3页

RCPG: Real-Time Product Path Guiding Using Radiance Cascades RCPG：使用辐射级联的实时产品路径引导

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-08-12 DOI: 10.1145/3840291

Julius Ikkala, Pekka Jääskeläinen, Markku Mäkitalo

{"title":"RCPG: Real-Time Product Path Guiding Using Radiance Cascades","authors":"Julius Ikkala, Pekka Jääskeläinen, Markku Mäkitalo","doi":"10.1145/3840291","DOIUrl":"https://doi.org/10.1145/3840291","url":null,"abstract":"We present Radiance Cascade Path Guiding (RCPG), a real-time product path guiding method that improves upon previous state-of-the-art real-time path guiding methods both in quality and performance. We derive bounds for radiance intervals such that the direction of incoming light is not misrepresented by radiance cascades. This allows us to take advantage of the hierarchical nature of radiance cascades in a sampling process that takes the product of the incoming radiance and the material’s BSDF into account. It is also possible to compute the probability distribution function of RCPG sampling for any given direction, making it readily compatible with other sampling methods, such as multiple importance sampling (MIS) and unbiased ReSTIR. As a product sampling scheme, RCPG can use a single sampling method for producing scattering directions, as opposed to needing separate importance sampling schemes for incident radiance and the BSDF. Compared to prior state-of-the-art real-time path guiding methods utilizing multi-sample MIS, this allows RCPG to generally trace twice as many paths per pixel within a real-time frame rate. Because the data structure is defined in world space, it can be used to generate samples starting from off-screen path vertices, which is necessary for effective multi-bounce path guiding.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"1 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148709531","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 Neural Frame Streaming Framework with a Simultaneous Prior for End-cloud Collaborative Rendering 面向端云协同渲染的并行先验神经帧流框架

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-08-08 DOI: 10.1145/3832308

Hangming Fan, Yazhen Yuan, Yongyu Ding, Yuwen Chen, Hujun Bao, Yuchi Huo, Rui Wang

{"title":"A Neural Frame Streaming Framework with a Simultaneous Prior for End-cloud Collaborative Rendering","authors":"Hangming Fan, Yazhen Yuan, Yongyu Ding, Yuwen Chen, Hujun Bao, Yuchi Huo, Rui Wang","doi":"10.1145/3832308","DOIUrl":"https://doi.org/10.1145/3832308","url":null,"abstract":"Cloud rendering has gained much attention recently since it alleviates the client’s computing cost by distributing most of the rendering tasks on the cloud, and the rendered frames are compressed and streamed to a client device for display. However, the accessibility of cloud rendering is still limited by the network communication cost to stream high-resolution frames. By introducing neural networks into the video compression algorithms, SOTA methods have achieved a better compression ratio than existing video codecs like H.265. However, none of them are designed specifically for rendered content, in which features like motion vectors, albedo, and normal are readily available in nowadays rendering pipelines. We propose a new end-cloud collaborative rendering and streaming framework that generates these auxiliary features on both the end and cloud sides as a simultaneous prior, and utilizes this prior to guide both the encoding and decoding of frame compression. Our framework can empower low-end devices with high-end visual effects and reduce the cost of establishing high-speed network connections. Results show that our streaming pipeline is highly efficient and achieves higher compression ratio compared with standard video codecs and other neural compression methods.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"20 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148687910","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

Efficient Offset Mesh Generation with Preserved Features and Boundaries 具有保留特征和边界的高效偏移网格生成

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-07-27 DOI: 10.1145/3832781

Canjia Huang, Juan Cao, Bailin Deng, Jiangbo Huang, Ge Yin, Zhonggui Chen

引用次数: 0

Pitfalls of Projection: A study of Newton-type solvers for incremental potentials 投影的陷阱：增量势的牛顿型求解器的研究

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-07-23 DOI: 10.1145/3829351

Andreas Longva, Fabian Löschner, José Fernández-Fernández, Egor Larionov, Uri Ascher, Jan Bender

{"title":"Pitfalls of Projection: A study of Newton-type solvers for incremental potentials","authors":"Andreas Longva, Fabian Löschner, José Fernández-Fernández, Egor Larionov, Uri Ascher, Jan Bender","doi":"10.1145/3829351","DOIUrl":"https://doi.org/10.1145/3829351","url":null,"abstract":"Nonlinear systems arising from time integrators like Backward Euler can sometimes be reformulated as optimization problems, known as incremental potentials. We show through a comprehensive experimental analysis that the widely used Projected Newton method, which relies on unconditional semidefinite projection of Hessian contributions, typically exhibits a reduced convergence rate compared to classical Newton’s method. We demonstrate how factors like resolution, element order, projection method, material model and boundary handling impact convergence of Projected Newton and Newton. Drawing on these findings, we propose the hybrid method Project-on-Demand Newton , which projects only conditionally , and show that it enjoys both the robustness of Projected Newton and convergence rate of Newton. We additionally introduce Kinetic Newton , a regularization-based method that takes advantage of the structure of incremental potentials and avoids projection altogether. We compare the four solvers on hyperelasticity and contact problems. We also present a nuanced discussion of convergence criteria, and show that a criterion based on the balance of acceleration avoids problems associated with existing residual norm criteria and is easier to interpret. We finally address a fundamental limitation of the backtracking line search that occasionally blocks convergence, especially for stiff problems. To overcome this issue, we propose a novel robust line search correction that does not require additional parameters.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"32 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148552171","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

HIL: Hybrid Imitation Learning for Dynamic Athletic Control 动态运动控制的混合模仿学习

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-07-15 DOI: 10.1145/3829364

Jiashun Wang, Yifeng Jiang, Haotian Zhang, Chen Tessler, Davis Rempe, Jessica Hodgins, Xue Bin Peng

{"title":"HIL: Hybrid Imitation Learning for Dynamic Athletic Control","authors":"Jiashun Wang, Yifeng Jiang, Haotian Zhang, Chen Tessler, Davis Rempe, Jessica Hodgins, Xue Bin Peng","doi":"10.1145/3829364","DOIUrl":"https://doi.org/10.1145/3829364","url":null,"abstract":"Data-driven methods leveraging deep reinforcement learning have become the dominant paradigm for developing controllers that enable physically simulated characters to produce natural human-like behaviors. However, these data-driven methods often struggle to adapt to novel environments and compose diverse skills to perform more complex interaction tasks with the environment. To address these challenges, we propose a hybrid imitation learning (HIL) framework that combines motion tracking, for precise skill replication, with adversarial imitation learning, to enhance adaptability and skill composition, enabling robust dynamic control for highly athletic behaviors. This hybrid learning framework is implemented through parallel multi-task environments and a unified observation space, utilizing a goal-conditioned representation to facilitate knowledge-sharing across the hybrid parallel environments. We demonstrate the effectiveness of HIL on a parkour-style obstacle traversal task and a heading control task. Our framework enables a unified controller that not only preserves the naturalness of reference motion data, but also generalizes effectively to challenging new environments. Evaluations across procedurally generated tasks and baselines show that our method improves motion quality, increases skill diversity, and achieves competitive task completion compared to previous learning-based approaches. Results are best visualized through https://jiashunwang.github.io/HIL.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"447 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148440799","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

Closed-Form Convolution for physically-accurate defocus in Gaussian Splatting 高斯溅射中物理精确离焦的闭合形式卷积

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-07-10 DOI: 10.1145/3821567

Weichen Dai, Kangcheng Ma, Wanzeng Kong

{"title":"Closed-Form Convolution for physically-accurate defocus in Gaussian Splatting","authors":"Weichen Dai, Kangcheng Ma, Wanzeng Kong","doi":"10.1145/3821567","DOIUrl":"https://doi.org/10.1145/3821567","url":null,"abstract":"Recent advancements in 3D Gaussian Splatting (3DGS) have achieved impressive photorealism; however, its foundational assumption of perfectly sharp, all-in-focus imagery often breaks down in real-world scenarios. Lens-induced defocus blur, common in natural captures, can significantly degrade reconstruction quality. While prior work has attempted to address this, existing solutions either rely on implicit deblurring, restricting post-capture artistic flexibility, or employ physically inaccurate blur approximations, particularly under large apertures. We present a rendering pipeline that seamlessly integrates a physically accurate and differentiable depth-of-field model into the 3D Gaussian Splatting (3DGS) rasterization process. At its core, our method models defocus by convolving each projected 3D Gaussian with a kernel shaped by the camera’s Circle of Confusion (CoC). To maintain efficiency, we derive a closed-form analytical solution for this convolution using the error function (erf). Our approach further extends to anisotropic Gaussians and approximates arbitrary polygonal apertures by decomposing them into non-overlapping rectangles. As a result, our method enables high-fidelity 3D reconstruction from blurry, multi-focus image sets, while supporting realistic post-capture effects such as refocusing and aperture manipulation. Experiments on defocus-focused benchmarks show that our technique yields visibly sharper in-focus details and smoother defocus transitions, delivering results competitive with the current best-performing methods.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"34 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148414777","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

DMP: Directable Motion Retargeting through Motion Paraphrasing DMP：通过动作释义的定向动作重定向

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-07-09 DOI: 10.1145/3829359

Sunmin Lee, Davis Rempe, Yifeng Jiang, Haotian Zhang, Tingwu Wang, Jungdam Won, Xue Bin Peng

{"title":"DMP: Directable Motion Retargeting through Motion Paraphrasing","authors":"Sunmin Lee, Davis Rempe, Yifeng Jiang, Haotian Zhang, Tingwu Wang, Jungdam Won, Xue Bin Peng","doi":"10.1145/3829359","DOIUrl":"https://doi.org/10.1145/3829359","url":null,"abstract":"Creating diverse and realistic human motions is a fundamental cornerstone of computer animation, with numerous applications in games, movies, and AR/VR. While motion capture is a valuable tool for capturing motions across varied body sizes, obtaining unique motion data for a variety of characters is often prohibitively expensive. Motion retargeting addresses this limitation by adapting existing motions to different character morphologies, however, existing approaches often involve trade-offs between motion realism, user control, and adaptability to artistic needs. In this work, we propose Directable Motion Paraphrasing (DMP), a novel motion retargeting framework based on the concept of motion paraphrasing , analogous to text paraphrasing, where the core semantics of a motion are preserved while allowing expressive, user-directed variations. Our framework constructs a large-scale motion paraphrasing dataset, which captures the diversity of human motion across different body shapes, and trains a diffusion-based generative model that learns both invariances and variations in motion. To enable user control during inference, we introduce a flexible mechanism for specifying spatio-temporal constraints, such as joint positions, rotations, and object interactions, which can be incorporated into the generative process through masked inpainting and loss guidance. We demonstrate the effectiveness of our framework through various examples, showing its ability to produce realistic, diverse, and controllable retargeted motions that meet the artistic demands of animation pipelines. Extensive experiments demonstrate the system’s flexibility, motion plausibility, and directability, highlighting its potential as a tool for intuitive and high-quality motion retargeting.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"445 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148408809","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

Robust Constrained Tetrahedralization with Steiner-point-free Boundaries 具有steiner无点边界的鲁棒约束四面体化

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-07-09 DOI: 10.1145/3829358

Yifu Wang, KaiXin Yu, Haonan Ni, Bohan Wang, Hang Si, Jianjun Chen

{"title":"Robust Constrained Tetrahedralization with Steiner-point-free Boundaries","authors":"Yifu Wang, KaiXin Yu, Haonan Ni, Bohan Wang, Hang Si, Jianjun Chen","doi":"10.1145/3829358","DOIUrl":"https://doi.org/10.1145/3829358","url":null,"abstract":"We introduce a robust algorithm for generating tetrahedral meshes that strictly conform to the geometry and connectivity of valid non-self-intersecting piecewise-linear complexes (PLCs). A key challenge in this task is the control of Steiner point placement. While optimizing Steiner point placement is NP-hard, eliminating boundary Steiner points remains practically important for preserving boundary topology and interface connectivity. To address this challenge, we introduce the concept of flip-hard configurations (FHCs), which characterize local situations where constraint recovery cannot proceed using flip operations alone. Based on this observation, we enhance the classical boundary recovery pipeline with FHC-guided interior Steiner insertion, robust boundary Steiner relocation, and local mesh optimization under floating-point arithmetic. These mechanisms reduce the reliance on boundary Steiner points and mitigate numerical failures caused by finite-precision rounding. We evaluate the proposed algorithm on all 5,468 valid models from the Thingi10K dataset. In these experiments, the implementation successfully produced constrained tetrahedralizations for all models, and all generated meshes contain Steiner-point-free boundaries while preserving the input PLC topology.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"64 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148408800","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

Hi-SPAD: Video-Rate Hyperspectral Imaging and Inference with Single-Photon Cameras Hi-SPAD：视频速率高光谱成像与单光子相机推理

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-07-08 DOI: 10.1145/3829360

Haejoon Lee, Mohit Gupta, Vijayakumar Bhagavatula, Aswin Sankaranarayanan

{"title":"Hi-SPAD: Video-Rate Hyperspectral Imaging and Inference with Single-Photon Cameras","authors":"Haejoon Lee, Mohit Gupta, Vijayakumar Bhagavatula, Aswin Sankaranarayanan","doi":"10.1145/3829360","DOIUrl":"https://doi.org/10.1145/3829360","url":null,"abstract":"We present Hi-SPAD, a hyperspectral imaging system that combines a pushbroom architecture with single-photon avalanche diode (SPAD) sensors to enable high spatial, spectral and temporal resolutions under passive ambient light. While SPAD-based spectral sensing and the pushbroom configuration have been explored separately, our key contribution lies in combining these technologies while addressing SPAD-specific challenges. We provide a theoretical analysis showing that, despite the heavily quantized and nonlinear nature of SPAD measurements, accurate material classification and full-spectrum reconstruction can be achieved with exponentially decreasing error bounds as the number of measurements increases. These results are validated through simulations and real data from our lab prototype, establishing the feasibility of photon-counting hyperspectral video in dynamic scenes. Additionally, we evaluate reconstruction methods for Hi-SPAD that support robust imaging under passive ambient illumination. Our lab-built Hi-SPAD camera enables hyperspectral video at 26 frames per second with 123 spectral channels, even under ambient lighting.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"41 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148401513","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

Unified Gaussian Primitives for Scene Representation and Rendering 用于场景表示和渲染的统一高斯原语

IF 6.2 1区计算机科学

ACM Transactions on Graphics Pub Date : 2026-07-07 DOI: 10.1145/3829352

Yang Zhou, Songyin Wu, Lingqi Yan

{"title":"Unified Gaussian Primitives for Scene Representation and Rendering","authors":"Yang Zhou, Songyin Wu, Lingqi Yan","doi":"10.1145/3829352","DOIUrl":"https://doi.org/10.1145/3829352","url":null,"abstract":"Searching for a unified scene representation remains a research challenge in computer graphics. Traditional mesh-based representations are unsuitable for dense, fuzzy elements and introduce additional complexity for filtering and differentiable rendering. Conversely, voxel-based representations struggle to model hard surfaces and high-frequency details. We propose a general-purpose rendering primitive based on 3D Gaussian distributions for unified scene representation, featuring versatile appearance ranging from glossy surfaces to fuzzy elements, as well as physically based scattering to enable accurate global illumination. We formulate the rendering theory for the primitive based on non-exponential transport and derive efficient rendering operations to be compatible with Monte Carlo path tracing. The new representation can be converted from different sources, including meshes and 3D Gaussian splatting, and further refined via transmittance optimization thanks to its differentiability. We demonstrate the versatility of our representation in various rendering applications such as global illumination and appearance editing, while naturally supporting arbitrary lighting conditions. With suitable simplification, we further adapt our method to radiance field reconstruction and rendering. We conduct comprehensive comparisons of our representation with existing scene representations, highlighting its efficiency in capturing details and representing aggregate elements.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"14 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148401135","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