Generating diverse clothed 3D human animations via a generative model  

作　　者：Min Shi Wenke Feng Lin Gao Dengming Zhu 

机构地区：[1]School of Control and Computer Engineering,North China Electric Power University,Beijing 102206,China [2]Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China

出　　处：《Computational Visual Media》2024年第2期261-277,共17页计算可视媒体（英文版）

基　　金：supported by the National Natural Science Foundation of China(Grant No.61972379).

摘　　要：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 twostage 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.

关 键 词：Transformer garment animation conditional variational autoencoder(CVAE) computer graphics 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]