ACM Transactions on Graphics最新文献

{"title":"Progressing Level-of-Detail Animation for Volumetric Elastodynamics","authors":"Jiayi Eris Zhang, Doug James, Danny Kaufman","doi":"10.1145/3811383","DOIUrl":"https://doi.org/10.1145/3811383","url":null,"abstract":"We extend Progressive Dynamics [Zhang et al. 2024, 2025] from cloth and shells to volumetric finite elements, enabling an efficient level-of-detail (LOD) animation-design pipeline with predictive coarse-resolution previews for rapid iteration toward a final high-resolution volumetric elastodynamics animation. To achieve this, we introduce <jats:italic toggle=\"yes\">VelPro Splitter</jats:italic> , a principled and substantially improved VelPro-type integrator [Zhang et al. 2025] that splits the current-level velocity and recombines its high-resolution component with prolonged coarse-level velocity. The resulting VelPro Splitter is general and applies to both shell and volumetric discretizations. This splitting strategy better generates the high-frequency dynamic details that motivate highresolution elastodynamics animation, going beyond the previously mostly geometric enrichment due to prolonged coarse-level velocity, while maintaining cross-level consistency in bulk deformation across LOD results. As a result, it largely decouples finest-level enrichment quality from the number of LOD levels, addressing a practical limitation of VelPro at small timestep sizes where many levels are required to obtain sufficient enrichment. To make this volumetric setting practical for Progressive Dynamics, we add two supporting contributions. First, we construct volumetric hierarchies and introduce a simple and effective topology-aware boundary-binding method that enables reliable prolongation between overlapping, but not-necessarily-conforming, meshes using a barycentric-like linear interpolant. Second, instead of applying the subspace approach of Zhang et al. [2024] for reducing coarse model locking, we show that a lightweight, resolution-based stiffness rescaling via a simple Young's-modulus adjustment [Chen et al. 2017] is both effective and well-suited for progressive volumetric simulation. Together, these contributions jointly realize Volumetric Progressive Dynamics. We demonstrate its high-fidelity LOD matching for volumetric elastodynamics across 1D, 2D, and 3D scenarios with high speeds, large deformations, and frictional contact.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"202 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372011","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}

{"title":"Strips as Tokens: Artist Mesh Generation with Native UV Segmentation","authors":"Rui Xu, Dafei Qin, Kaichun Qiao, Qiujie Dong, Huaijin Pi, Qixuan Zhang, Longwen Zhang, Lan Xu, Jingyi Yu, Wenping Wang, Taku Komura","doi":"10.1145/3811286","DOIUrl":"https://doi.org/10.1145/3811286","url":null,"abstract":"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 ( <jats:italic toggle=\"yes\">SATO</jats:italic> ), 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 <jats:italic toggle=\"yes\">SATO</jats:italic> consistently outperforms prior methods in terms of geometric quality, structural coherence, and UV segmentation.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"23 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372014","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}

{"title":"GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization","authors":"Chenxi Liu, Selena Ling, Alec Jacobson","doi":"10.1145/3811293","DOIUrl":"https://doi.org/10.1145/3811293","url":null,"abstract":"Fine-tuning-based adaptation is widely used to customize diffusion-based image generation, leading to large collections of community-created adapters that capture diverse subjects and styles. Adapters derived from the same base model can be merged linearly, enabling the synthesis of new visual results within a vast and continuous design space. To explore this space, current workflows rely on manual slider-based tuning, an approach that scales poorly and makes merging coefficient selection difficult, even when the candidate set is limited to 20–30 adapters. We propose GimmBO to support interactive exploration of adapter merging for image generation through Preferential Bayesian Optimization (PBO). Motivated by observations from real-world usage, including sparsity and constrained coefficient ranges, we introduce a two-stage BO backend that improves sampling efficiency and convergence in high-dimensional spaces. We evaluate our approach with simulated users and a user study, demonstrating improved convergence, high success rates, and consistent gains over BO and line-search baselines, and further show the flexibility of the framework through several extensions.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"8 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372032","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}

{"title":"ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models","authors":"Rui Xu, Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Shiqing Xin, Changhe Tu, Taku Komura, Wenping Wang","doi":"10.1145/3811285","DOIUrl":"https://doi.org/10.1145/3811285","url":null,"abstract":"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 <jats:italic toggle=\"yes\">ComboStoc.</jats:italic> Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes. Moreover, <jats:italic toggle=\"yes\">ComboStoc</jats:italic> 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.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"1 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372139","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}

{"title":"Surface Power Diagrams for Knit Singularity Placement","authors":"Rahul Mitra, Mattéo Couplet, Ruichen Liu, Jonathan Ng, Ruza Markov, William Batara Jeremiah Samosir, Megan Hofmann, Edward Chien","doi":"10.1145/3811401","DOIUrl":"https://doi.org/10.1145/3811401","url":null,"abstract":"We present an algorithm for global knit structure planning that leverages a generalization of power diagrams to triangulated surfaces. This generalization is based on modified geodesic heat kernels and is used to quantize the curl measure of a normalized knitting time function gradient. Knit singularity positions are optimized jointly in a global fashion via an iterative Lloyd-type algorithm, leading to faster and more optimal placement of singularities than prior work, allowing for practical creation of denser knit graphs. In this denser setting, we present singularity ordering constraints that more robustly achieve helix-free knit graphs. The speed and robustness of the method is demonstrated via a diverse array of knits, and a virtual gallery of helix-free knit graphs. We also provide further demonstration of user constraints for knit singularity masking, level set alignment constraints, and apparent seam placement via curl boosting.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"61 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372147","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}

{"title":"ToF ReSTIR: Time-of-Flight Rendering with Spatio-temporal Reservoir Resampling","authors":"Juhyeon Kim, Wojciech Jarosz, Adithya Pediredla","doi":"10.1145/3811299","DOIUrl":"https://doi.org/10.1145/3811299","url":null,"abstract":"We present a novel spatio-temporal reuse framework for time-resolved light transport, enabling efficient Monte Carlo rendering of time-of-flight (ToF) phenomena such as time-gated imaging and transient light capture. Existing ToF rendering methods are computationally expensive, scale poorly to complex dynamic scenes, and are therefore unsuitable for applications with strict latency constraints. To address this limitation, we draw inspiration from <jats:italic toggle=\"yes\">ReSTIR</jats:italic> , a reuse-based technique for steady-state real-time rendering, and adapt its core principles to interactive-rate ToF simulation. However, naively applying existing ReSTIR methods to ToF rendering leads to severe inefficiency, as reused paths frequently violate optical path-length constraints and thus contribute little or no signal. We overcome this challenge by introducing a path reuse formulation that explicitly enforces physically valid optical path lengths. The key idea is <jats:italic toggle=\"yes\">path-length-aware shift mapping</jats:italic> , a geometric transformation based on Newton's method that adjusts reused light paths to satisfy temporal gating constraints, inspired by specular manifold exploration in steady-state caustics rendering. The resulting framework substantially improves the efficiency of ToF rendering across a wide range of scenarios, including complex scenes with glossy or specular materials and dynamic motion. Our method supports both time-gated and transient rendering at interactive frame rates, enabling simulation under practical latency constraints. We demonstrate the effectiveness of our approach through two downstream applications, including shape reconstruction and navigation.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"27 1 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372150","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}

{"title":"Manifold k-NN: Accelerated k-NN Queries for Manifold Point Clouds","authors":"Pengfei Wang, Qinghao Guo, Haisen Zhao, Shiqing Xin, Shuangmin Chen, Changhe Tu, Wenping Wang","doi":"10.1145/3811271","DOIUrl":"https://doi.org/10.1145/3811271","url":null,"abstract":"<jats:italic toggle=\"yes\">k</jats:italic> -nearest neighbor ( <jats:italic toggle=\"yes\">k</jats:italic> -NN) search is a fundamental primitive in geometry processing and computer graphics. While spatial partitioning structures such as <jats:italic toggle=\"yes\">kd</jats:italic> -trees are standard, they are often manifold-blind, failing to exploit the intrinsic low-dimensional structure of points sampled from 2-manifolds. Recent advances in dynamic programming-based nearest neighbor search (DP-NNS) leverage incrementally constructed Voronoi diagrams to accelerate queries, where each site <jats:italic toggle=\"yes\">p</jats:italic> maintains a list of <jats:italic toggle=\"yes\">successors</jats:italic> that progressively refine its Voronoi cell. However, DP-NNS is restricted to single nearest neighbor ( <jats:italic toggle=\"yes\">k</jats:italic> = 1) searches, precluding their adoption in applications that require local neighborhood statistics. In this paper, we generalize the DP-NNS framework to support arbitrary <jats:italic toggle=\"yes\">k</jats:italic> -NN queries for manifold-aligned data. Our approach is founded on the geometric observation that if <jats:italic toggle=\"yes\"> p <jats:sub>i</jats:sub> </jats:italic> is the nearest neighbor of a query <jats:italic toggle=\"yes\">q</jats:italic> in <jats:italic toggle=\"yes\">P</jats:italic> , then the second nearest neighbor of <jats:italic toggle=\"yes\">q</jats:italic> must reside either within the prefix set <jats:italic toggle=\"yes\">P</jats:italic> <jats:sub> 1: <jats:italic toggle=\"yes\">i</jats:italic> -1 </jats:sub> = [ <jats:italic toggle=\"yes\">p</jats:italic> <jats:sub>1</jats:sub> , ..., <jats:italic toggle=\"yes\">p</jats:italic> <jats:sub>i-1</jats:sub> } or within <jats:italic toggle=\"yes\"> p <jats:sub>i</jats:sub> </jats:italic> 's successor list. By recursively extending this principle, we introduce Manifold <jats:italic toggle=\"yes\">k</jats:italic> -NN, a recursive algorithmic scheme that significantly outperforms conventional <jats:italic toggle=\"yes\">kd</jats:italic> -trees for manifold-aligned data. Our method achieves a 1×-10× speedup in volume-to-surface query scenarios and inherently supports <jats:italic toggle=\"yes\">dynamic prefix</jats:italic> queries—enabling <jats:italic toggle=\"yes\">k</jats:italic> -NN searches within any subset <jats:italic toggle=\"yes\">P</jats:italic> <jats:sub> 1: <jats:italic toggle=\"yes\">m</jats:italic> </jats:sub> ( <jats:italic toggle=\"yes\">m</jats:italic> ≤ <jats:italic toggle=\"yes\">n</jats:italic> ) with zero overhead. Furthermore, we extend the framework to support point deletion via local Delaunay updates, providing a complete suite of dynamic operations for point set modification. Comprehensive experiments on diverse geometric datasets demonstrate the efficiency and broad applicability of our approach for modern graphics pipelines. Source code is available at https://github.com/sssomeone/manifold-knn.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"80 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372272","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}

{"title":"MeshFEM: A Block-accelerated Solver for Nonlinear Finite Elements","authors":"Haleh Mohammadian, Xinzhuo Hu, Roi Poranne, Julian Panetta","doi":"10.1145/3811386","DOIUrl":"https://doi.org/10.1145/3811386","url":null,"abstract":"We introduce a high-performance framework for solving nonconvex optimization problems arising in simulation and geometry processing applications. Our framework especially benefits high-dimensional problems whose unknowns are spatial coordinates in ℝ <jats:sup> <jats:italic toggle=\"yes\">d</jats:italic> </jats:sup> and whose objectives are expressed as a sum of element energies over small stencils. The Hessians of these problems have a block-sparse structure, where the nonzero entries are grouped into dense <jats:italic toggle=\"yes\">d</jats:italic> × <jats:italic toggle=\"yes\">d</jats:italic> blocks. Many works have exploited this structure to speed up the Hessian-vector products and nodal smoothers of iterative solvers. In contrast, accelerating direct sparse linear solvers, preferred for applications requiring high accuracy on unstructured grids, has been less explored. Our framework leverages block structure to accelerate all phases of a Newton-type minimization algorithm, from sparsity pattern construction to system assembly, matrix factorization, and solves. A fundamental piece of the framework is BlockCatamari, our highly tuned, block-accelerated multifrontal sparse Cholesky code that achieves significantly faster factorizations than existing direct solvers on shared-memory systems. We combine this solver with our fast parallel Hessian assembly routine, heuristics for conditionally enabling per-element Hessian projections, and strategies for minimizing symbolic factorization re-computations. We show that this leads to dramatic speedups on a large suite of benchmark problems involving injective surface parametrization and elasticity simulation with contact, and we further demonstrate the ease with which new energies can be defined at the different levels of abstraction offered by our framework.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"23 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372273","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}

{"title":"Locality-Aware Automatic Differentiation on the GPU for Mesh-Based Computations","authors":"Ahmed Mahmoud, Rahul Goel, Jonathan Ragan-Kelley, Justin Solomon","doi":"10.1145/3811338","DOIUrl":"https://doi.org/10.1145/3811338","url":null,"abstract":"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 perelement 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, Dr.JIT, 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.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"31 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372308","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}

{"title":"ProXeek: Seeking and Leveraging Real-World Objects and Environments as Haptic Proxies for Virtual Reality through Multimodal Reasoning","authors":"Haichen Gao, Tianrui Hu, Zeshui Li, Kening Zhu","doi":"10.1145/3811349","DOIUrl":"https://doi.org/10.1145/3811349","url":null,"abstract":"Providing haptic feedback in virtual reality (VR) remains challenging, with active haptic systems often being bulky and expensive, while passive haptics typically require pre-fabricated objects or extensive real-world setup. We present ProXeek, an LLM-based multi-agent system that opportunistically leverages real-world objects as haptic proxies for VR experiences. During VR development, the designers could annotate the virtual interactables with emphasized haptic characteristics using our node-based editing interface. On the user side, end users capture environmental snapshots via commodity VR headset, and the system employs LLM-based multimodal reasoning and multi-objective optimization to match virtual objects with viable physical proxies. Our technical evaluation demonstrates that ProXeek effectively identifies viable proxies, confirming the effectiveness of the algorithmic constraint design in our matching pipeline. Our user study further reveals that the ProXeek-selected physical objects could deliver significantly higher haptic fidelity and enhance presence compared to 3D-printed replicas and visual-only interaction.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"202 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148371869","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}