paper-with-me

홈 › Papers

GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects

2024-12-23 · Yidi Shao, Mu Huang, Chen Change Loy, Bo Dai

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 .

📄 PDF Abstract BibTeX arXiv:2412.17804

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

Real-time simulation of viscoelastic tissue behavior with physics-guided deep learning

2023-01-11 · Mohammad Karami, Hervé Lombaert, David Rivest-Hénault

Finite element methods (FEM) are popular approaches for simulation of soft tissues with elastic or viscoelastic behavior. However, their usage in real-time applications, such as in virtual reality surgical training, is l…

Deep Learning

Learning 3D-Gaussian Simulators from RGB Videos

2025-03-31 · Mikel Zhobro, Andreas René Geist, Georg Martius

Learning physics simulations from video data requires maintaining spatial and temporal consistency, a challenge often addressed with strong inductive biases or ground-truth 3D information -- limiting scalability and gene…

Inverse Rendering

Simplicits: Mesh-Free, Geometry-Agnostic, Elastic Simulation

2024-06-09 · Vismay Modi, Nicholas Sharp, Or Perel, Shinjiro Sueda 외

The proliferation of 3D representations, from explicit meshes to implicit neural fields and more, motivates the need for simulators agnostic to representation. We present a data-, mesh-, and grid-free solution for elasti…

Neural Modular Physics for Elastic Simulation

2025-12-17 · Yifei Li, Haixu Wu, Zeyi Xu, Tuur Stuyck 외 arxiv

Learning-based methods have made significant progress in physics simulation, typically approximating dynamics with a monolithic end-to-end optimized neural network. Although these models offer an effective way to simulat…

Microcosmos: Reimagining Artificial Life for the GPU Era

2026-07-03 · Mark Tensen, Ciaran Regan, Bert Wang-Chak Chan, Mizuki Oka 외 arxiv

Most artificial life simulators either operate on abstract substrates disconnected from physical reality, or simulate physically grounded worlds that do not scale to the population sizes required for open-ended evolution…