Yi Wang is a Ph.D. Student, Zhi-Qiang Liu and Li-Zhu Zhou are professors.
1546-427X/asset/CAV_left.gif?v=1&s=2241761cd5fadd2ab7722ff1e6970e096e2cdd54)
1546-427X/asset/CAV_right.gif?v=1&s=1398f59d5daab6a1919d8434b98a56fe172cb9e9)
Research Article
Key-styling: learning motion style for real-time synthesis of 3D animation†
Article first published online: 14 JUN 2006
DOI: 10.1002/cav.126
Copyright © 2006 John Wiley & Sons, Ltd.
Issue
1546-427X/asset/cover.gif?v=1&s=bf6e65177d0877921b695716e7abb7b41f1feca4 "Computer Animation and Virtual Worlds")
Computer Animation and Virtual Worlds
Special Issue: CASA 2006
Volume 17, Issue 3-4, pages 229–237, July 2006
Additional Information
How to Cite
Wang, Y., Liu, Z.-Q. and Zhou, L.-Z. (2006), Key-styling: learning motion style for real-time synthesis of 3D animation. Comp. Anim. Virtual Worlds, 17: 229–237. doi: 10.1002/cav.126
- †
Publication History
- Issue published online: 14 JUN 2006
- Article first published online: 14 JUN 2006
- Manuscript Accepted: 10 MAY 2006
- Manuscript Revised: 2 MAY 2006
- Manuscript Received: 10 APR 2006
Funded by
- Hong Kong RGC. Grant Numbers: 1062/02E, CityU 1247/03E
- Natural Science Foundation of China. Grant Number: 60573061
- Abstract
- References
- Cited By
Keywords:
- motion synthesis;
- motion capture data;
- neural networks;
- self-organizing mixture network
Abstract
In this paper, we present a novel real-time motion synthesis approach that can generate 3D character animation with required style. The effectiveness of our approach comes from learning captured 3D human motion as a self-organizing mixture network (SOMN); of parametric Gaussians.The learned model describes the motion under the control of a vector variable called style variable, and acts as a probabilistic mapping from the low-dimensional style values to the high-dimensional 3D poses. We design a pose synthesis algorithm to allow the user to generate poses by specifying new style values. We also propose a novel motion synthesis method, the key-styling, which accepts a sparse sequence of key style values and interpolates a dense sequence of style values to synthesize an animation. Key-styling is able to produce animations that are more realistic and natural-looking than those synthesized with the traditional key-keyframing technique. Copyright © 2006 John Wiley & Sons, Ltd.