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 will be released. Project page: https://www.mmlab-ntu.com/project/gausim/index.html .

翻译：我们提出GausSim，一种新颖的基于神经网络的模拟器，旨在捕捉通过高斯核表示的现实世界弹性物体的动态行为。我们利用连续介质力学，将每个核视为代表连续物质单元的质心系统，在无需理想化假设的情况下实现真实形变建模。为提高计算效率与保真度，我们采用分层结构将核进一步组织为具有显式表达式的质心系统，实现从粗到精的模拟过程。该结构在保持精细动力学特征的同时显著降低了计算开销。此外，GausSim整合了质量守恒与动量守恒等显式物理约束，确保结果可解释且模拟过程稳健、符合物理规律。为验证方法有效性，我们构建了包含真实弹性形变多视角视频的新数据集READY。实验结果表明，与现有物理驱动基线相比，GausSim实现了更优的性能，为复杂动态行为模拟提供了实用且精确的解决方案。代码与模型将公开。项目页面：https://www.mmlab-ntu.com/project/gausim/index.html。