Neural Modes: Self-supervised Learning of Nonlinear Modal Subspaces

Jiahong Wang, Yinwei Du, Stelian Coros, Bernhard Thomaszewski; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 23158-23167

We propose a self-supervised approach for learning physics-based subspaces for real-time simulation. Existing learning-based methods construct subspaces by approximating pre-defined simulation data in a purely geometric way. However this approach tends to produce high-energy configurations leads to entangled latent space dimensions and generalizes poorly beyond the training set. To overcome these limitations we propose a self-supervised approach that directly minimizes the system's mechanical energy during training. We show that our method leads to learned subspaces that reflect physical equilibrium constraints resolve overfitting issues of previous methods and offer interpretable latent space parameters.