Motion Guided Deep Dynamic 3D Garments
This addresses the challenge of authoring dynamic garment geometry for AR/VR, offering a data-driven simulation alternative that is incremental in its approach.
The paper tackles the problem of generating realistic dynamic 3D garments for animated characters in AR/VR applications by developing a data-driven method that predicts garment deformations based on character motion, showing improvements over state-of-the-art alternatives and plausible generalization to unseen shapes and motions.
Realistic dynamic garments on animated characters have many AR/VR applications. While authoring such dynamic garment geometry is still a challenging task, data-driven simulation provides an attractive alternative, especially if it can be controlled simply using the motion of the underlying character. In this work, we focus on motion guided dynamic 3D garments, especially for loose garments. In a data-driven setup, we first learn a generative space of plausible garment geometries. Then, we learn a mapping to this space to capture the motion dependent dynamic deformations, conditioned on the previous state of the garment as well as its relative position with respect to the underlying body. Technically, we model garment dynamics, driven using the input character motion, by predicting per-frame local displacements in a canonical state of the garment that is enriched with frame-dependent skinning weights to bring the garment to the global space. We resolve any remaining per-frame collisions by predicting residual local displacements. The resultant garment geometry is used as history to enable iterative rollout prediction. We demonstrate plausible generalization to unseen body shapes and motion inputs, and show improvements over multiple state-of-the-art alternatives.