Fracture-GS: Dynamic Fracture Simulation with Physics-Integrated Gaussian Splatting
Xiaogang Wang, Hongyu Wu, Wenfeng Song, Kai Xu
摘要
This paper presents a unified framework for simulating and visualizing dynamic fracture phenomena in extreme mechanical collisions using multi-view image inputs. While existing methods primarily address elastic deformations at contact surfaces, they fail to capture the complex physics of extreme collisions, often producing non-physical artifacts and material adhesion at fracture interfaces. Our approach integrates two key innovations: (1) an enhanced Collision Material Point Method (Collision-MPM) with momentum-conserving interface forces derived from normalized mass distributions, which effectively eliminates unphysical adhesion in fractured solids; and (2) a fracture-aware 3D Gaussian continuum representation that enables physically plausible rendering without post-processing. The framework operates through three main stages: First, performing implicit reconstruction of collision objects from multi-view images while sampling both surface and internal particles and simultaneously learning surface particle Gaussian properties via splatting; Second, high-fidelity collision resolution using our improved Collision-MPM formulation; Third, dynamic fracture tracking with Gaussian attribute optimization for fracture surfaces rendering. Through comprehensive testing, our framework demonstrates significant improvements over existing methods in handling diverse scenarios, including homogeneous materials, heterogeneous composites, and complex multi-body collisions. The results confirm superior physical accuracy, while maintaining computational efficiency for rendering.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper12
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- 4D Gaussian Splatting for Real-Time Dynamic Scene RenderingGuanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie 等CVPR 2024 · 被引用 513 次
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene ReconstructionZiyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao 等CVPR 2024 · 被引用 302 次
- NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance FieldsLiangchen Song, Anpei Chen, Zhong Li, Zhang Chen 等IEEE VR 2023 · 被引用 246 次
- PhysGaussian: Physics-Integrated 3D Gaussians for Generative DynamicsTianyi Xie, Zeshun Zong, Yuxing Qiu, Xuan Li 等CVPR 2024 · 被引用 118 次
相关 Paper
- GaussianFluent: Gaussian Simulation for Dynamic Scenes with Mixed MaterialsBei Huang, Yixin Chen, Ruijie Lu, Gang Zeng 等CVPR 2026 · 被引用 5 次
- MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based DynamicsChangmin Lee, Jihyun Lee, Tae-Kyun KimNeurIPS 2025 · 被引用 9 次
- A Dynamic Duo of Finite Elements and Material PointsXuan Li, Minchen Li, Xuchen Han, Huamin Wang 等SIGGRAPH 2024 · 被引用 8 次
- Gaussian-Augmented Physics Simulation and System Identification with Complex CollidersFederico Vasile, Ri-Zhao Qiu, Lorenzo Natale, Xiaolong WangNeurIPS 2025 · 被引用 4 次
- A massively parallel and scalable multi-CPU material point methodXinlei Wang, Yuxing Qiu, Stuart R. Slattery, Yu Fang 等SIGGRAPH 2020 · 被引用 82 次
