Learning a Correlated Model of Identity and Pose-Dependent Body Shape Variation for Real-Time Synthesis
Loading...
Date
2006
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
We present a method for learning a model of human body shape variation from a corpus of 3D range scans. Our model is the first to capture both identity-dependent and pose-dependent shape variation in a correlated fashion, enabling creation of a variety of virtual human characters with realistic and non-linear body deformations that are customized to the individual. Our learning method is robust to irregular sampling in pose-space and identityspace, and also to missing surface data in the examples. Our synthesized character models are based on standard skinning techniques and can be rendered in real time.
Description
@inproceedings{10.2312:SCA/SCA06/147-156,
booktitle = {ACM SIGGRAPH / Eurographics Symposium on Computer Animation},
editor = {Marie-Paule Cani and James O'Brien},
title = {{Learning a Correlated Model of Identity and Pose-Dependent Body Shape Variation for Real-Time Synthesis}},
author = {Allen, Brett and Curless, Brian and Popovic, Zoran and Hertzmann, Aaron},
year = {2006},
publisher = {The Eurographics Association},
ISSN = {1727-5288},
ISBN = {3-905673-34-7},
DOI = {10.2312/SCA/SCA06/147-156}
}