Neural Modes: Self-supervised Learning of Nonlinear Modal Subspaces
This addresses the issue of high-energy configurations and poor generalization in existing learning-based methods for real-time simulation, though it appears incremental as it builds on prior geometric approaches.
The paper tackled the problem of learning physics-based subspaces for real-time simulation by proposing a self-supervised approach that minimizes mechanical energy during training, resulting in subspaces that reflect physical equilibrium constraints, resolve overfitting, and offer interpretable latent parameters.
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.