Style learning and transferring for facial animation editing

Xiaohan Ma, Binh Huy Le, and Zhigang Deng

ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA) 2009

A set of example poses are
decomposed into rigid bone transformations B and a sparse, convex bone-vertex
weight map W (left hand side) by our block coordinate descent algorithm (right
hand side). During the process, the example poses (indicated as blue dots) can
be reconstructed more accurately by alternatively updating W and B while the
other is kept fixed.

Abstract: Most of current facial animation editing techniques are frame-based approaches (i.e., manually edit one keyframe every several frames), which is ineffective, time-consuming, and prone to editing inconsistency. In this paper, we present a novel facial editing style learning framework that is able to learn a constraint-based Gaussian Process model from a small number of facial-editing pairs, and then it can be effectively applied to automate the editing of the remaining facial animation frames or transfer editing styles between different animation sequences. Comparing with the state of the art, multiresolution-based mesh sequence editing technique, our approach is more flexible, powerful, and adaptive. Our approach can dramatically reduce the manual efforts required by most of current facial animation editing approaches.

Download: [paper] [video]

Bibtex

@inproceedings{XiaohanMa:SCA:2009,
author = {Ma, Xiaohan and Le, Binh Huy and Deng, Zhigang},
title = {Style learning and transferring for facial animation editing},
booktitle = {Proceedings of the 2009 ACM SIGGRAPH/Eurographics Symposium on Computer Animation},
series = {SCA '09},
year = {2009},
isbn = {978-1-60558-610-6},
location = {New Orleans, Louisiana},
pages = {123--132},
numpages = {10},
url = {http://doi.acm.org/10.1145/1599470.1599486},
doi = {10.1145/1599470.1599486},
acmid = {1599486},
publisher = {ACM},
address = {New York, NY, USA},
}