Self-supervised Learning of Latent Space Dynamics 57
Open Access
- 8 August 2025
- journal article
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 8 (4) , 1-18
Abstract
Modeling the dynamic behavior of deformable objects is crucial for creating realistic digital worlds. While conventional simulations produce high-quality motions, their computational costs are often prohibitive. Subspace simulation techniques address this challenge by restricting deformations to a lower-dimensional space, improving performance while maintaining visually compelling results. However, even subspace methods struggle to meet the stringent performance demands of portable devices such as virtual reality headsets and mobile platforms. To overcome this limitation, we introduce a novel subspace simulation framework powered by a neural latent-space integrator. Our approach leverages self-supervised learning to enhance inference stability and generalization. By operating entirely within latent space, our method eliminates the need for full-space computations, resulting in a highly efficient method well-suited for deployment on portable devices. We demonstrate the effectiveness of our approach on challenging examples involving rods, shells, and solids, showcasing its versatility and potential for widespread adoption.Keywords
All Related Versions
This publication has 60 references indexed in Scilit:
- Neural Modes: Self-supervised Learning of Nonlinear Modal Subspaces2024
- HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics2023
- Model reduction for the material point method via an implicit neural representation of the deformation mapJournal of Computational Physics, 2023
- SNUG: Self-Supervised Neural Dynamic Garments2022
- Deep Physics-aware Inference of Cloth Deformation for Monocular Human Performance Capture2021
- PyTorch2021
- Real-Time Hair Simulation With Neural InterpolationIEEE Transactions on Visualization and Computer Graphics, 2020
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencodersJournal of Computational Physics, 2020
- Deep Residual Learning for Image Recognition2016
- Numerical Optimization1999