ElastoGen: 4D Generative Elastodynamics
This work addresses the challenge of physically accurate 4D generation for materials science and engineering, offering a novel integration of physics with deep learning.
The paper tackled the problem of generating physically accurate 4D elastodynamics by introducing ElastoGen, a knowledge-driven AI model that leverages physics principles instead of learning from observations, resulting in a lightweight model that efficiently generates accurate dynamics for hyperelastic materials.
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.