ElastoGen: 4D Generative Elastodynamics
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917071852404736 |
|---|---|
| author | Feng, Yutao Shang, Yintong Feng, Xiang Lan, Lei Zhe, Shandian Shao, Tianjia Wu, Hongzhi Zhou, Kun Jiang, Chenfanfu Yang, Yin |
| author_facet | Feng, Yutao Shang, Yintong Feng, Xiang Lan, Lei Zhe, Shandian Shao, Tianjia Wu, Hongzhi Zhou, Kun Jiang, Chenfanfu Yang, Yin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_15056 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ElastoGen: 4D Generative Elastodynamics Feng, Yutao Shang, Yintong Feng, Xiang Lan, Lei Zhe, Shandian Shao, Tianjia Wu, Hongzhi Zhou, Kun Jiang, Chenfanfu Yang, Yin Machine Learning Computer Vision and Pattern Recognition Graphics 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. |
| title | ElastoGen: 4D Generative Elastodynamics |
| topic | Machine Learning Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2405.15056 |