ShapeVerse: Physics-based Characters with Varied Body Shapes
No Thumbnail Available
Date
2024
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Computer animation of realistic human characters remains a significant challenge. This work used deep reinforcement learning to generate physics-based characters with diverse body shapes. We aimed to replicate reference motions like walking or jogging while considering individual variations in body shape and mass. Reference motions served as training targets, accounting for differences in shape parameters to accommodate mass variations. This method produced animations that accurately capture human motion details, leading to diverse and lifelike character performances.
Description
CCS Concepts: Computing methodologies → Physical simulation; Procedural animation; Motion capture
@inproceedings{10.2312:egp.20241042,
booktitle = {Eurographics 2024 - Posters},
editor = {Liu, Lingjie and Averkiou, Melinos},
title = {{ShapeVerse: Physics-based Characters with Varied Body Shapes}},
author = {Vyas, Bharat and O'Sullivan, Carol},
year = {2024},
publisher = {The Eurographics Association},
ISSN = {1017-4656},
ISBN = {978-3-03868-239-4},
DOI = {10.2312/egp.20241042}
}