A Repulsive Force Unit for Garment Collision Handling in Neural Networks
This addresses garment-body collision issues in 3D garment simulation for applications like virtual try-on and animation, representing an incremental improvement over existing collision handling techniques.
The paper tackles the problem of interpenetration between garments and bodies in 3D garment deformation prediction by proposing a Repulsive Force Unit (ReFU) neural network layer, which significantly reduces collisions and better preserves geometric details compared to prior methods.
Despite recent success, deep learning-based methods for predicting 3D garment deformation under body motion suffer from interpenetration problems between the garment and the body. To address this problem, we propose a novel collision handling neural network layer called Repulsive Force Unit (ReFU). Based on the signed distance function (SDF) of the underlying body and the current garment vertex positions, ReFU predicts the per-vertex offsets that push any interpenetrating vertex to a collision-free configuration while preserving the fine geometric details. We show that ReFU is differentiable with trainable parameters and can be integrated into different network backbones that predict 3D garment deformations. Our experiments show that ReFU significantly reduces the number of collisions between the body and the garment and better preserves geometric details compared to prior methods based on collision loss or post-processing optimization.