PhysSkin++: A real-time general-purpose physics animation framework based on self-supervised neural skinning
PhysSkin++ proposes a physics-informed framework that learns a continuous neural skinning field from static geometry, constructs a compact deformation subspace, and generalizes across shapes without per-object network training. Its neural skinning field autoencoder, combined with a physics-informed self-supervised learning strategy, stably jointly optimizes without simulation trajectories, and supports direct animation rigging of meshes, point clouds, and 3D Gaussians as well as real-time reduced-dimension simulation. Experiments validate applications including cross-shape generalization, real-time simulation, and controllable collision-aware animation.