PhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning

Researchers introduced PhysSkin++, a physics-informed framework that learns continuous neural skinning fields from static geometries to build a compact deformation subspace, addressing the challenge of generalizing real-time physics-based animation across diverse 3D shapes and spatial discretizations. The work is presented as a paper describing a self-supervised neural skinning approach for physics-based animation.

Generalizing real-time physics-based animation across diverse 3D shapes and spatial discretizations remains challenging. In this paper, we introduce PhysSkin++, a physics-informed framework that learns continuous neural skinning fields from static geometries to construct compact deformation subspace