GauSim: Registering Elastic Objects into Digital World by Gaussian Simulator

ArXiv, 2024

Foresee Dynamics in Real World

Interactive Dynamics

The

Abstract

In this work, we introduce GauSim, a novel neural network-based simulator designed to capture the dynamic behaviors of real-world elastic objects represented through Gaussian kernels. Unlike traditional methods that treat kernels as particles within particle-based simulations, we leverage continuum mechanics, modeling each kernel as a continuous piece of matter to account for realistic deformations without idealized assumptions. To improve computational efficiency and fidelity, we employ a hierarchical structure that organizes kernels into Center of Mass Systems (CMS), enabling a coarse-to-fine simulation approach. This structure significantly reduces computational overhead while preserving detailed dynamics. In addition, GauSim 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 GauSim achieves superior performance compared to existing physics-driven baselines, offering a practical and accurate solution for simulating complex dynamic behaviors.

Experiments

Qualitative Results

Comparing with Ground Truth (Real Videos)

More Comparisons

The

GauSim

Our GauSim integrates with physics in the following ways:

  1. We formulate GauSim based on continuum mechanics.
  2. We propose a hierarchical structure with interpretable formulations for the simulation process.
  3. We constrain GauSim with mass and momentum conservation in an explicit manner.

Paper

Citation

@InProceedings{shao2024gausim,
 author = {Shao, Yidi and Loy, Chen Change and Dai, Bo},
 title = {GauSim: Registering Elastic Objects into Digital World by Gaussian Simulator},
 booktitle = {CoRR},
 year = {2024}
}

Contact


Shao Yidi
Email: yidi001 at e.ntu.edu.sg