ElastoGen: 4D Generative Elastodynamics

TL;DR

ElastoGen is a physics-based AI model that efficiently generates accurate 4D elastodynamics by translating differential equations into iterative convolution operations, requiring less training and network complexity than traditional deep models.

Contribution

ElastoGen introduces a physics-driven approach converting nonlinear force equilibrium equations into convolutional operations, enabling lightweight and accurate 4D elastodynamics generation.

Findings

Achieves physically accurate 4D elastodynamics generation

Requires less training data and smaller network scale

Easily integrates with deep modules for end-to-end processes

Abstract

We present ElastoGen, a knowledge-driven AI model that generates physically accurate 4D elastodynamics. Unlike deep models that learn from video- or image-based observations, ElastoGen leverages the principles of physics and learns from established mathematical and optimization procedures. The core idea of ElastoGen is converting the differential equation, corresponding to the nonlinear force equilibrium, into a series of iterative local convolution-like operations, which naturally fit deep architectures. We carefully build our network module following this overarching design philosophy. ElastoGen is much more lightweight in terms of both training requirements and network scale than deep generative models. Because of its alignment with actual physical procedures, ElastoGen efficiently generates accurate dynamics for a wide range of hyperelastic materials and can be easily integrated with upstream and downstream deep modules to enable end-to-end 4D generation.