Bingchen Yang, Haiyong Jiang, Hao Pan, Guosheng Lin, Jun Xiao, Peter Wonka
{"title":"PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction","authors":"Bingchen Yang, Haiyong Jiang, Hao Pan, Guosheng Lin, Jun Xiao, Peter Wonka","doi":"10.1145/3733595","DOIUrl":"https://doi.org/10.1145/3733595","url":null,"abstract":"Reverse engineering CAD models from raw geometry is a classic but challenging research problem. In particular, reconstructing the CAD modeling sequence from point clouds provides great interpretability and convenience for editing. Analyzing previous work, we observed that a CAD modeling sequence represented by tokens and processed by a generative model does not have an immediate geometric interpretation. To improve upon this problem, we introduce geometric guidance into the reconstruction network. Our proposed model, PS-CAD, reconstructs the CAD modeling sequence one step at a time as illustrated in Fig. 1. At each step, we provide three forms of geometric guidance. First, we provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud. This helps the framework to focus on regions that still need work. Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces where a CAD extrusion step could be started. Third, we present a step-wise sampling to generate multiple complete candidate CAD modeling steps instead of single-tokens without direct geometric interpretation. Our framework has three major components. Geometric guidance computation extracts the first two types of geometric guidance. Single-step reconstruction computes a single candidate CAD modeling step for each provided prompt. Single-step selection selects among the candidate CAD modeling steps. The process continues until the reconstruction is completed. Our quantitative results show a significant improvement across all metrics. For example, on the dataset DeepCAD, PS-CAD improves upon the best published SOTA method by reducing the geometry errors (CD and HD) by <jats:inline-formula content-type=\"math/tex\"> <jats:tex-math notation=\"TeX\" version=\"MathJaX\">(10% )</jats:tex-math> </jats:inline-formula> , and the structural error (ECD metric) by about <jats:inline-formula content-type=\"math/tex\"> <jats:tex-math notation=\"TeX\" version=\"MathJaX\">(13% )</jats:tex-math> </jats:inline-formula> .","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"142 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143927018","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}
Kemeng Huang, Xinyu Lu, Huancheng Lin, Taku Komura, Minchen Li
{"title":"StiffGIPC: Advancing GPU IPC for Stiff Affine-Deformable Simulation","authors":"Kemeng Huang, Xinyu Lu, Huancheng Lin, Taku Komura, Minchen Li","doi":"10.1145/3735126","DOIUrl":"https://doi.org/10.1145/3735126","url":null,"abstract":"Incremental Potential Contact (IPC) is a widely used, robust, and accurate method for simulating complex frictional contact behaviors. However, achieving high efficiency remains a major challenge, particularly as material stiffness increases, which leads to slower Preconditioned Conjugate Gradient (PCG) convergence, even with the state-of-the-art preconditioners. In this paper, we propose a fully GPU-optimized IPC simulation framework capable of handling materials across a wide range of stiffnesses, delivering consistent high performance and scalability with up to 10 × speedup over state-of-the-art GPU IPC methods. Our framework introduces three key innovations: 1) A novel connectivity-enhanced Multilevel Additive Schwarz (MAS) preconditioner on the GPU, designed to efficiently capture both stiff and soft elastodynamics and improve PCG convergence at a reduced preconditioning cost. 2) A <jats:italic>C</jats:italic> <jats:sup>2</jats:sup> -continuous cubic energy with an analytic eigensystem for inexact strain limiting, enabling more parallel-friendly simulations of stiff membranes, such as cloth, without membrane locking. 3) For extremely stiff behaviors where elastic waves are barely visible, we employ affine body dynamics (ABD) with a hash-based two-level reduction strategy for fast Hessian assembly and efficient affine-deformable coupling. We conduct extensive performance analyses and benchmark studies to compare our framework against state-of-the-art methods and alternative design choices. Our system consistently delivers the fastest performance across soft, stiff, and hybrid simulation scenarios, even in cases with high resolution, large deformations, and high-speed impacts.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"63 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920277","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":"Reliable Iterative Dynamics: A Versatile Method for Fast and Robust Simulation","authors":"Jia-Ming Lu, Shi-Min Hu","doi":"10.1145/3734518","DOIUrl":"https://doi.org/10.1145/3734518","url":null,"abstract":"Simulating stiff materials has long posed formidable challenges for traditional physics-based solvers. Explicit time integration schemes demand prohibitively small time steps, while implicit methods necessitate an excessive number of iterations to converge, often yielding visually objectionable transient configurations in the early iterations, severely limiting their real-time applicability. Position-based dynamics techniques can efficiently simulate stiff constraints but are inherently restricted to constraint-based formulations, curtailing their versatility. We present ”Reliable Iterative Dynamics” (RID), a novel iterative solver that introduces a dual descent framework with theoretical guarantees for visual reliability at each iteration, while maintaining fast and stable convergence even for extremely stiff systems. Our core innovation is an iterative method that circumvents the need for numerous iterations or small time steps to handle stiff materials robustly. Experimental evaluations demonstrate our method’s ability to handle a wide range of materials, from soft to infinitely rigid, while producing visually reliable results even with large time steps and minimal iterations. The versatile formulation allows seamless integration with diverse simulation paradigms like the finite element method, material point method, smoothed particle hydrodynamics, and incremental potential contact for applications ranging from elastic body simulations to fluids and collision handling.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"197 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143909836","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":"End-to-end Surface Optimization for Light Control","authors":"Yuou Sun, Bailin Deng, Juyong Zhang","doi":"10.1145/3732284","DOIUrl":"https://doi.org/10.1145/3732284","url":null,"abstract":"Designing a freeform surface to reflect or refract light to achieve a target distribution is a challenging inverse problem. In this paper, we propose an end-to-end optimization strategy for an optical surface mesh. Our formulation leverages a novel differentiable rendering model, and is directly driven by the difference between the resulting light distribution and the target distribution. We also enforce geometric constraints related to fabrication requirements, to facilitate CNC milling and polishing of the designed surface. To address the issue of local minima, we formulate a face-based optimal transport problem between the current mesh and the target distribution, which makes effective large changes to the surface shape. The combination of our optimal transport update and rendering-guided optimization produces an optical surface design with a resulting image closely resembling the target, while the geometric constraints in our optimization help to ensure consistency between the rendering model and the final physical results. The effectiveness of our algorithm is demonstrated on a variety of target images using both simulated rendering and physical prototypes.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"138 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143901200","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}
Florian Andreas Schiffers, Grace Kuo, Nathan Matsuda, Douglas Lanman, Oliver Cossairt
{"title":"HoloChrome: Polychromatic Illumination for Speckle Reduction in Holographic Near-Eye Displays","authors":"Florian Andreas Schiffers, Grace Kuo, Nathan Matsuda, Douglas Lanman, Oliver Cossairt","doi":"10.1145/3732935","DOIUrl":"https://doi.org/10.1145/3732935","url":null,"abstract":"Holographic displays hold the promise of providing authentic depth cues, resulting in enhanced immersive visual experiences for near-eye applications. However, current holographic displays are hindered by speckle noise, which limits accurate reproduction of color and texture in displayed images. We present HoloChrome, a polychromatic holographic display framework designed to mitigate these limitations. HoloChrome utilizes an ultrafast, wavelength-adjustable laser and a dual-Spatial Light Modulator (SLM) architecture, enabling the multiplexing of a large set of discrete wavelengths across the visible spectrum. By leveraging spatial separation in our dual-SLM setup, we independently manipulate speckle patterns across multiple wavelengths. This novel approach effectively reduces speckle noise through incoherent averaging achieved by wavelength multiplexing, specifically by using a single SLM pattern to modulate multiple wavelengths simultaneously on one or more SLM devices. Our method is complementary to existing speckle reduction techniques, offering a new pathway to address this challenge. Furthermore, the use of polychromatic illumination broadens the achievable color gamut compared to traditional three-color primary holographic displays. Our simulations and tabletop experiments validate that HoloChrome significantly reduces speckle noise and expands the color gamut. These advancements enhance the performance of holographic near-eye displays, moving us closer to practical, immersive next-generation visual experiences.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"45 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143884855","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}
Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Taku Komura, Wenping Wang
{"title":"StructRe : Rewriting for Structured Shape Modeling","authors":"Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Taku Komura, Wenping Wang","doi":"10.1145/3732934","DOIUrl":"https://doi.org/10.1145/3732934","url":null,"abstract":"Man-made 3D shapes are naturally organized in parts and hierarchies; such structures provide important constraints for shape reconstruction and generation. Modeling shape structures is difficult, because there can be multiple hierarchies for a given shape, causing ambiguity, and across different categories the shape structures are correlated with semantics, limiting generalization. We present <jats:italic>StructRe</jats:italic> , a structure rewriting system, as a novel approach to structured shape modeling. Given a 3D object represented by points and components, <jats:italic>StructRe</jats:italic> can rewrite it upward into more concise structures, or downward into more detailed structures; by iterating the rewriting process, hierarchies are obtained. Such a localized rewriting process enables probabilistic modeling of ambiguous structures and robust generalization across object categories. We train <jats:italic>StructRe</jats:italic> on PartNet data and show its generalization to cross-category and multiple object hierarchies, and test its extension to ShapeNet. We also demonstrate the benefits of probabilistic and generalizable structure modeling for shape reconstruction, generation and editing tasks.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"27 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143884860","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":"Policy-Space Diffusion for Physics-Based Character Animation","authors":"Michele Rocca, Sune Darkner, Kenny Erleben, Sheldon Andrews","doi":"10.1145/3732285","DOIUrl":"https://doi.org/10.1145/3732285","url":null,"abstract":"Adapting motion to new contexts in digital entertainment often demands fast agile prototyping. State-of-the-art techniques use reinforcement learning policies for simulating the underlined motion in a physics engine. Unfortunately, policies typically fail on unseen tasks and it is too time-consuming to fine-tune the policy for every new morphological, environmental, or motion change. We propose a novel point of view on using policy networks as a representation of motion for physics-based character animation. Our policies are compact, tailored to individual motion tasks, and preserve similarity with nearby tasks. This allows us to view the space of all motions as a manifold of policies where sampling substitutes training. We obtain memory-efficient encoding of motion that leverages the characteristics of control policies such as being generative, and robust to small environmental changes. With this perspective, we can sample novel motions by directly manipulating weights and biases through a Diffusion Model. Our newly generated policies can adapt to previously unseen characters, potentially saving time in rapid prototyping scenarios. Our contributions include the introduction of Common Neighbor Policy regularization to constrain policy similarity during motion imitation training making them suitable for generative modeling; a Diffusion Model adaptation for diverse morphology; and an open policy dataset. The results show that we can learn non-linear transformations in the policy space from labeled examples, and conditionally generate new ones. In a matter of seconds, we sample a batch of policies for different conditions that show comparable motion fidelity metrics as their respective trained ones.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"6 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143875758","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":"A Neural Particle Level Set Method for Dynamic Interface Tracking","authors":"Duowen Chen, Junwei Zhou, Bo Zhu","doi":"10.1145/3730399","DOIUrl":"https://doi.org/10.1145/3730399","url":null,"abstract":"We propose a neural particle level set (Neural PLS) method to accommodate tracking and evolving dynamic neural representations. At the heart of our approach is a set of oriented particles serving dual roles of interface trackers and sampling seeders. These dynamic particles are used to evolve the interface and construct neural representations on a multi-resolution grid-hash structure to hybridize coarse sparse distance fields and multi-scale feature encoding. Based on these parallel implementations and neural-network-friendly architectures, our neural particle level set method combines the computational merits on both ends of the traditional particle level sets and the modern implicit neural representations, in terms of feature representation and dynamic tracking. We demonstrate the efficacy of our approach by showcasing its performance surpassing traditional level-set methods in both benchmark tests and physical simulations.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"28 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143853216","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":"MoFlow: Motion-Guided Flows for Recurrent Rendered Frame Prediction","authors":"Zhizhen Wu, Zhilong Yuan, Chenyu Zuo, Yazhen Yuan, Yifan PENG, Guiyang Pu, Rui Wang, Yuchi Huo","doi":"10.1145/3730400","DOIUrl":"https://doi.org/10.1145/3730400","url":null,"abstract":"Rendering realistic images in real-time on high-frame-rate display devices poses considerable challenges, even with advanced graphics cards. This stimulates a demand for frame prediction technologies to boost frame rates. The key to these algorithms is to exploit spatiotemporal coherence by warping rendered pixels with motion representations. However, existing motion estimation methods can suffer from low precision, high overhead, and incomplete support for visual effects. In this article, we present a rendered frame prediction framework with a novel motion representation, dubbed <jats:italic>motion-guided flow (MoFlow)</jats:italic> , aiming to overcome the intrinsic limitations of optical flow and motion vectors and precisely capture the dynamics of intricate geometries, lighting, and translucent objects. Notably, we construct MoFlows using a recurrent feature streaming network, which specializes in learning latent motion features from multiple frames. The results of extensive experiments demonstrate that, compared to state-of-the-art methods, our method achieves superior visual quality and temporal stability with lower latency. The recurrent mechanism allows our method to predict single or multiple consecutive frames, increasing the frame rate by over 2 ×. The proposed approach represents a flexible pipeline to meet the demands of various graphics applications, devices, and scenarios.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"10 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849781","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}
Guying Lin, Lei Yang, Congyi Zhang, Hao Pan, Yuhan Ping, Guodong Wei, Taku Komura, John Keyser, Wenping Wang
{"title":"Patch-Grid : An Efficient and Feature-Preserving Neural Implicit Surface Representation","authors":"Guying Lin, Lei Yang, Congyi Zhang, Hao Pan, Yuhan Ping, Guodong Wei, Taku Komura, John Keyser, Wenping Wang","doi":"10.1145/3727142","DOIUrl":"https://doi.org/10.1145/3727142","url":null,"abstract":"Neural implicit representations are increasingly used to depict 3D shapes owing to their inherent smoothness and compactness, contrasting with traditional discrete representations. Yet, the multilayer perceptron (MLP) based neural representation, because of its smooth nature, rounds sharp corners or edges, rendering it unsuitable for representing objects with sharp features like CAD models. Moreover, neural implicit representations need long training times to fit 3D shapes. While previous works address these issues separately, we present a unified neural implicit representation called <jats:italic>Patch-Grid</jats:italic> , which efficiently fits complex shapes, preserves sharp features delineating different patches, and can also represent surfaces with open boundaries and thin geometric features. <jats:italic>Patch-Grid</jats:italic> learns a signed distance field (SDF) to approximate an encompassing surface patch of the shape with a learnable patch feature volume. To form sharp edges and corners in a CAD model, <jats:italic>Patch-Grid</jats:italic> merges the learned SDFs via the constructive solid geometry (CSG) approach. Core to the merging process is a novel <jats:italic>merge grid</jats:italic> design that organizes different patch feature volumes in a common octree structure. This design choice ensures robust merging of multiple learned SDFs by confining the CSG operations to localized regions. Additionally, it drastically reduces the complexity of the CSG operations in each merging cell, allowing the proposed method to be trained in seconds to fit a complex shape at high fidelity. Experimental results demonstrate that the proposed <jats:italic>Patch-Grid</jats:italic> representation is capable of accurately reconstructing shapes with complex sharp features, open boundaries, and thin geometric elements, achieving state-of-the-art reconstruction quality with high computational efficiency within seconds.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"183 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805704","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}