Learning a correlated model of identity and pose-dependent
body shape variation for real-time synthesis
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 identity space, 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.
ALLEN, B., CURLESS, B., POPOVIĆ, Z., and HERTZMANN, A. 2006. Learning a correlated model of identity and pose-dependent body shape variation for real-time synthesis. In Proc. of the 2006 ACM SIGGRAPH/Eurographics symposium on Computer animation, p. 147-156, Sept. 2-4, Vienna, Austria.
BibTeX entry:
@inproceedings{allen06learning,
author = "Brett Allen and Brian Curless and Zoran Popovi{\'{c}} and Aaron Hertzmann",
title = "Learning a correlated model of identity and pose-dependent body shape variation for real-time synthesis",
booktitle = "Proceedings of the 2006 ACM SIGGRAPH/Eurographics symposium on Computer animation",
year = "2006",
pages = "147--156",
location = "Vienna, Austria",
publisher = "Eurographics Association",
address = "Aire-la-Ville, Switzerland",
}