Generating diverse clothed 3D human animations via a generative model
Open Access
- 1 April 2024
- journal article
- research article
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (2) , 261-277
Abstract
Data-driven garment animation is a current topic of interest in the computer graphics industry. Existing approaches generally establish the mapping between a single human pose or a temporal pose sequence, and garment deformation, but it is difficult to quickly generate diverse clothed human animations. We address this problem with a method to automatically synthesize dressed human animations with temporal consistency from a specified human motion label. At the heart of our method is a two-stage strategy. Specifically, we first learn a latent space encoding the sequence-level distribution of human motions utilizing a transformer-based conditional variational autoencoder (Transformer-CVAE). Then a garment simulator synthesizes dynamic garment shapes using a transformer encoder–decoder architecture. Since the learned latent space comes from varied human motions, our method can generate a variety of styles of motions given a specific motion label. By means of a novel beginning of sequence (BOS) learning strategy and a self-supervised refinement procedure, our garment simulator is capable of efficiently synthesizing garment deformation sequences corresponding to the generated human motions while maintaining temporal and spatial consistency. We verify our ideas experimentally. This is the first generative model that directly dresses human animation.Keywords
This publication has 41 references indexed in Scilit:
- SMPLACM Transactions on Graphics, 2015
- Sensitivity-optimized rigging for example-based real-time clothing synthesisACM Transactions on Graphics, 2014
- Adaptive anisotropic remeshing for cloth simulationACM Transactions on Graphics, 2012
- DRAPEACM Transactions on Graphics, 2012
- Example-based wrinkle synthesis for clothing animationACM Transactions on Graphics, 2010
- A Perception Correlated Comparison Method for Dynamic MeshesIEEE Transactions on Visualization and Computer Graphics, 2010
- Large steps in cloth simulation1998
- Collision and self-collision handling in cloth model dedicated to design garments1997
- A signal processing approach to fair surface design1995
- Collision and Self-Collision Detection: Efficient and Robust Solutions for Highly Deformable Surfaces1995