ACM Transactions on Graphics最新文献

{"title":"The PhaseTree: Multiphase Signed Distance Fields","authors":"Eric Galin, Pierre Hubert-briere, Marie-Paule Cani, Adrien Peytavie, Eric Guérin, Hugo Schott","doi":"10.1145/3811379","DOIUrl":"https://doi.org/10.1145/3811379","url":null,"abstract":"We introduce the PhaseTree, a novel hierarchical construction-tree representation for compactly modeling volumetric objects composed of multiple phases or materials across scales. An object is defined as a single construction tree that combines phase-aware primitives through composition and warping operators, yielding a unified multiphase signed distance representation that naturally supports complex topologies and interfaces between phases. The PhaseTree is compatible with standard signed distance field workflows: single-phase algorithms can be directly promoted to a PhaseTree, and conversely reduced without loss of information. As a result, our model integrates seamlessly with existing algorithms and rendering pipelines. We extend classical Sphere Tracing to robustly handle multiphase configurations and show that, despite the additional expressiveness, our implementation preserves the compactness and resolution independence of signed distance fields and incurs less than a 25% runtime overhead compared to single-phase Sphere Tracing.","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":"148372148","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":"MUSIC: Learning Muscle-Driven Dexterous Hand Control","authors":"Pei Xu, Yufei Ye, Shuchu Sun, Yu Ding, Elizabeth Schumann, C. Karen Liu","doi":"10.1145/3811402","DOIUrl":"https://doi.org/10.1145/3811402","url":null,"abstract":"We present a data-driven approach for physics-based, muscle-driven dexterous control that enables musculoskeletal hands to perform precise piano playing for novel pieces of music outside the reference dataset. Our approach combines high-frequency muscle-level control with low-frequency latent-space coordination in a hierarchical architecture. At the low level, general single-hand policies are trained via reinforcement learning to generate dynamic muscle-tendon activations while tracking trajectories from a large reference motion dataset. The resulting tracking policies are then distilled into variational autoencoder (VAE) models, yielding smooth and structured latent spaces that abstract away low-level muscle dynamics. For the high level, we train piece-specific policies to operate in this latent space, coordinating bimanual motions based on specific goals, denoted by note events extracted from given musical scores, to synthesize performances beyond the reference data. High-level control is formulated as a decentralized multiagent reinforcement learning problem combined with adversarial learning for motion imitation. In addition, we present an enhanced musculoskeletal hand model that supports fine control of fingers for accurate low-level motion tracking and diverse high-level motion synthesis. We evaluate the control pipeline of our approach on a diverse piano repertoire spanning multiple musical styles and technical demands. Results demonstrate that our approach can synthesize coordinated bimanual motions with accurate key presses, and achieve the state-of-the-art performance of piano playing in physics-based dexterous control, while generalizing to sheet music that is not presented in the reference dataset. We also show that our musculoskeletal hand model demonstrates superior biomechanical stability and tracking precision compared to the existing model, and validate that our musculoskeletal hand model and muscle-driven controller can generate physiologically plausible activation patterns that align with human electromyography (EMG) recordings when subjects perform multiple tasks.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"35 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372151","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":"Constant Mean Curvature Surfaces from Discrete Harmonic Maps","authors":"Yousuf Soliman, Peter Schröder, Ulrich Pinkall","doi":"10.1145/3811370","DOIUrl":"https://doi.org/10.1145/3811370","url":null,"abstract":"Constant mean curvature surfaces are æsthetically appealing geometric objects with applications in physics, differential geometry, and architecture. We present a straightforward discretization of constant mean curvature surfaces based on the classical observation that their Gauß maps are harmonic. Our construction is elementary—requiring only discrete Dirichlet energy minimization and a Poisson solve—yet it exactly mirrors this aspect of the smooth theory. A discrete analog of conjugation produces discrete constant Gauß curvature surfaces. Their unit offsets are discrete CMC surfaces with a conformal parameterization. Additionally, we introduce a novel Möbius-invariant discretization of the Dirichlet energy for sphere-valued maps on dual meshes that is derived from the discrete Willmore energy. It is more robust than standard formulations based on inverse cotangent weights. Our approach to the construction of constant mean curvature surfaces provides direct control over tangent planes along a boundary, if present, and naturally handles closed and periodic examples. We demonstrate the approach on a range of free-boundary, symmetric, and periodic CMC surfaces.","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":"148372282","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":"TOG 45(4) Editorial","authors":"Mirela Ben-Chen","doi":"10.1145/3815597","DOIUrl":"https://doi.org/10.1145/3815597","url":null,"abstract":"We are pleased to introduce the special issue of TOG and SIGGRAPH Conference Proceedings which includes all papers accepted to the SIGGRAPH 2026 conference. This year, we received an extraordinary 1177 complete submissions, out of which 216 submissions were journal-only and 961 submissions were dual-track. The Technical Papers Committee (PC), composed of 111 experts from academia and industry, accepted 327 submissions: 132 as Journal papers (97 from the journal-only track and 35 from the dual-track) and 195 as Conference papers, resulting in an overall acceptance rate of 27%.","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":"148371865","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":"High-Fidelity 4D Cloth Capture Pipeline with a Two-Level Pattern","authors":"Ziheng Liu, Anka Chen, Shu Chen, Yin Yang, Cem Yuksel, Jenny Han Lin","doi":"10.1145/3811305","DOIUrl":"https://doi.org/10.1145/3811305","url":null,"abstract":"Capturing cloth motion with high fidelity is challenging due to fine-scale wrinkles, large deformation, and frequent self-occlusion. We present a 4D (spatio-temporal) cloth capture system that achieves 1 mm spatial resolution using only 16 RGB cameras. Our approach uses a two-level marker pattern: sparse, colored L-shaped markers provide robust detection and orientation, while dense noise patterns within each marker enable both marker identification and precise keypoint localization. By unwarping detected markers to a canonical frame, we factor out perspective distortion and most of cloth deformation, allowing the localizer to achieve sub-pixel accuracy. The localized keypoints are triangulated across views to form an incomplete point cloud. A physics-based optimization then deforms a template mesh to match the captured geometry while maintaining penetration-free constraints and physical plausibility for occluded regions. Our method produces temporally coherent sequences that faithfully capture fine wrinkles and folds even during complex motions with self-contact.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"32 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148371866","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":"Radiance Caching for Differentiable Path Tracing","authors":"Ziyi Zhang, Delio Vicini, Sebastian Winberg, Stephan Garbin, Wenzel Jakob","doi":"10.1145/3811398","DOIUrl":"https://doi.org/10.1145/3811398","url":null,"abstract":"Differentiable path tracing offers a principled route to recovering physical material and lighting parameters, but the combination of high variance and poor numerical conditioning often makes it too brittle to use in practice. This is especially the case when lighting is altogether unknown, or when the scene contains complex light transport effects. Prior work recently showed that the variance reduction provided by a radiance cache can alleviate these challenges. We revisit the combination of inverse rendering and radiance caching with a twist, by introducing a spatial blending field that locally interpolates between the cache and standard unbiased estimators. Recursive application of this idea yields a rich design space of evaluation strategies and inter-estimator consistency losses; we map this space and identify effective components. A surprising property of the resulting algorithm is that it can accurately recover material parameters even when the lighting is not uniquely identifiable from the observations. Our experiments demonstrate significant improvements in speed and robustness over prior work, making a strong case for including radiance caching as a standard component of future physically based inverse rendering systems.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"159 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148371930","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":"HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis","authors":"Haimin Luo, Min Ouyang, Lan Xu, Jingyi Yu","doi":"10.1145/3811350","DOIUrl":"https://doi.org/10.1145/3811350","url":null,"abstract":"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.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"11 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148371932","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":"Robust Planar Maps for 3D Vectorization","authors":"Robert Fuchs, Keenan Crane","doi":"10.1145/3811357","DOIUrl":"https://doi.org/10.1145/3811357","url":null,"abstract":"This paper describes a strategy for vectorizing 3D scenes with proper occlusion. Given a collection of curves derived from 3D geometry (silhouettes, isolines, material boundaries, etc.), we produce a 2D vector image that partitions the image plane into a <jats:italic toggle=\"yes\">planar map</jats:italic> of solid shaded regions. The method is agnostic to surface representation, handling for instance curves obtained from polygonal, NURBS or subdivision surfaces. The output likewise supports curve segments of arbitrary parametric type. Our key observation is that the spatial hierarchy used to accelerate curve-curve intersections provides the fundamental representation of the planar map itself. This approach provides geometric flexibility, since general curve-curve intersection problems are replaced with simpler curve-line intersection. Simultaneously, it provides robustness since cells of the spatial hierarchy define a well-defined planar map, even in the presence of numerical errors. For instance, it automatically handles \"curve soup\" where segment endpoints are not explicitly connected in the input file. The method scales to a large number of primitives, and is output sensitive: it resolves intersections only up to a user-defined precision—while still providing topologically valid output. We evaluate the method on a collection of challenging tests, showing that it is both more robust and orders of magnitude more efficient than existing curve arrangement techniques, such as those found in CGAL.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"116 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148371936","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":"Generative Modeling with Orbit-Space Particle Flow Matching","authors":"Sinan Wang, Jinjin He, Shenyifan Lu, Ruicheng Wang, Greg Turk, Bo Zhu","doi":"10.1145/3811342","DOIUrl":"https://doi.org/10.1145/3811342","url":null,"abstract":"We present Orbit-Space Geometric Probability Paths (OGPP) , a particle-native flow-matching framework for generative modeling of particle systems. OGPP is motivated by two insights: (i) particles are defined up to <jats:italic toggle=\"yes\">permutation symmetries</jats:italic> , so anonymous indexing inflates per-index target variance and yields curved, hard-to-learn flows; (ii) particles live in physical space, so the flow's <jats:italic toggle=\"yes\">terminal velocity</jats:italic> has physical meaning and can encode geometric attributes (e.g., surface normals). OGPP instantiates three key components: (1) orbit-space canonicalization of the probability-path terminal endpoint, (2) particle index embeddings for role specialization, and (3) geometric probability paths with arc-length-aware terminal velocities that generate normals as a byproduct of the flow. We evaluate OGPP on minimal-surface benchmarks, where it reduces metric error by up to two orders of magnitude in a single inference step; on ShapeNet, where it matches the state-of-the-art with 5× fewer steps and reaches airplane EMD comparable to DiT-3D with 26× fewer parameters and 5× fewer steps; and on single-shape encoding, where it produces normals and reconstructions competitive with 6D generators while operating entirely in 3D.","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":"148371986","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":"Tempo3D: Efficient Temporal-Aware Fine-Tuning and Multi-View Latent Aggregation for 3D Generation","authors":"Huizhi Zhu, Jiongming Qin, Yusen Wang, Chunxia Xiao","doi":"10.1145/3811362","DOIUrl":"https://doi.org/10.1145/3811362","url":null,"abstract":"Despite recent advancements in native latent diffusion models for single-view 3D generation, they still suffer from inadequate geometric details due to the global entanglement of VecSet-based representations and inaccurate structural topology arising from single-view ambiguity. Existing solutions often rely on model scaling over large-scale datasets to improve fidelity, which is computationally prohibitive and inefficient in capturing fine-grained details. In this work, we propose <jats:italic toggle=\"yes\">Tempo3D</jats:italic> , a resource-efficient paradigm for high-fidelity VecSet-based 3D generation via efficient temporal-aware fine-tuning and multi-view latent aggregation. Our approach consists of two critical components: (1) To facilitate robust detail learning, we establish the TempoDetail dataset and design the Time-Segmented LoRA (TS-LoRA) module. TS-LoRA exploits the inherent \"structure-to-details\" temporal transition of flow-based models to decouple feature learning, significantly bolstering the capacity to produce high-frequency details without large-scale retraining. (2) To mitigate geometric inaccuracies stemming from single-view ambiguity, we propose a multi-view latent aggregation strategy incorporating Soft Flow Trajectory Projection (Soft FTP) and Score-based Velocity Field Aggregation (SVFA). By aggregating reference views derived from Multimodal Large Language Models (MLLMs), these components resolve the intrinsic conflicts between velocity vectors caused by cross-view latent discrepancies, thereby preventing geometric collapse and ensuring directional consistency. Moreover, the integration of MLLMs empowers Tempo3D to support precise semantic 3D editing via natural language prompts while maintaining structural integrity. Experiments demonstrate that Tempo3D outperforms state-of-the-art baselines in generation quality, geometric precision, and editability under a highly efficient computational budget.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"32 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372009","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}