PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
This addresses a fundamental problem in computer graphics for animators and developers by providing a generalizable and efficient solution for physics-based animation.
The paper tackles the challenge of achieving real-time physics-based animation that generalizes across diverse 3D shapes and discretizations by introducing PhysSkin, a physics-informed framework that learns continuous skinning fields, resulting in outstanding performance and enabling real-time animation.
Achieving real-time physics-based animation that generalizes across diverse 3D shapes and discretizations remains a fundamental challenge. We introduce PhysSkin, a physics-informed framework that addresses this challenge. In the spirit of Linear Blend Skinning, we learn continuous skinning fields as basis functions lifting motion subspace coordinates to full-space deformation, with subspace defined by handle transformations. To generate mesh-free, discretization-agnostic, and physically consistent skinning fields that generalize well across diverse 3D shapes, PhysSkin employs a new neural skinning fields autoencoder which consists of a transformer-based encoder and a cross-attention decoder. Furthermore, we also develop a novel physics-informed self-supervised learning strategy that incorporates on-the-fly skinning-field normalization and conflict-aware gradient correction, enabling effective balancing of energy minimization, spatial smoothness, and orthogonality constraints. PhysSkin shows outstanding performance on generalizable neural skinning and enables real-time physics-based animation.