用高斯核模拟弹性物体，实现高效且物理真实的动态仿真。
GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects
- 将高斯核视为质心系统，基于连续介质力学建模真实形变。
- 采用分层结构，计算效率提升同时保留细节动态。
- 支持可解释的物理约束，适合需要真实仿真场景的研究者。
我们提出 GausSim，一种基于神经网络的新型模拟器，用于捕捉由高斯核表示的真实世界弹性物体的动态行为。通过连续介质力学原理，将每个高斯核视为质心系统（CMS），以连续物质片段建模，避免理想化假设，实现真实形变。为提升计算效率与保真度，引入分层结构，将高斯核进一步组织为具有显式公式的 CMS，支持粗粒度到细粒度的模拟策略。该结构显著降低计算开销，同时保持细节动力学。此外，GausSim 显式融入质量守恒、动量守恒等物理约束，确保结果可解释且物理上合理。为验证方法，我们构建了新数据集 READY，包含多视角真实弹性形变视频。实验表明，相较于现有物理驱动基线，GausSim 在性能上表现更优，提供了一种实用且精准的复杂动态行为模拟方案。代码与模型已公开于项目主页：https://www.mmlab-ntu.com/project/gausim/index.html。
原文摘要 · Abstract (English)
We introduce GausSim, a novel neural network-based simulator designed to capture the dynamic behaviors of real-world elastic objects represented through Gaussian kernels. We leverage continuum mechanics and treat each kernel as a Center of Mass System (CMS) that represents continuous piece of matter, accounting for realistic deformations without idealized assumptions. To improve computational efficiency and fidelity, we employ a hierarchical structure that further organizes kernels into CMSs with explicit formulations, enabling a coarse-to-fine simulation approach. This structure significantly reduces computational overhead while preserving detailed dynamics. In addition, GausSim incorporates explicit physics constraints, such as mass and momentum conservation, ensuring interpretable results and robust, physically plausible simulations. To validate our approach, we present a new dataset, READY, containing multi-view videos of real-world elastic deformations. Experimental results demonstrate that GausSim achieves superior performance compared to existing physics-driven baselines, offering a practical and accurate solution for simulating complex dynamic behaviors. Code and model are available at our project page: https://www.mmlab-ntu.com/project/gausim/index.html .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。