Generating diverse clothed 3D human animations via a generative model

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 animatio...

Full description

Saved in:
Bibliographic Details
Published in:Computational visual media (Beijing) Vol. 10; no. 2; pp. 261 - 277
Main Authors: Shi, Min, Feng, Wenke, Gao, Lin, Zhu, Dengming
Format: Journal Article
Language:English
Published: Beijing Tsinghua University Press 01.04.2024
Springer Nature B.V
SpringerOpen
Subjects:
Animation
Artificial Intelligence
Computer Graphics
Computer Science
Computers
conditional variational autoencoder (CVAE)
Consistency
Deformation
garment animation
Garments
Human motion
Image Processing and Computer Vision
Labels
Learning
Realism
Research Article
Semantics
Simulation
Special effects
Synthesis
Transformer
Transformers
User Interfaces and Human Computer Interaction
Virtual reality
garment animation
computer graphics
Transformer
conditional variational autoencoder (CVAE)
ISSN:2096-0433, 2096-0662
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2096-0433
2096-0662
DOI:10.1007/s41095-022-0324-2