Real-Time synthesis of 3d animations by learning parametric gaussians using self-organizing mixture networks

Authors:
Yi Wang;Hujun Yin;Li-Zhu Zhou;Zhi-Qiang Liu
Affiliations:
Department of Computer Science and Technology, Tsinghua University, Graduate School at Shenzhen, China;School of Electrical and Electronic Engineering, The University of Manchester, UK;Department of Computer Science and Technology, Tsinghua University, Graduate School at Shenzhen, China;School of Creative Media, City University of Hong Kong, Kowloon, Hong Kong
Venue:
ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
Year:
2006

Citing 6
Cited 0

Parametric Hidden Markov Models for Gesture Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Style machines

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Motion texture: a two-level statistical model for character motion synthesis

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Style-based inverse kinematics

ACM SIGGRAPH 2004 Papers
Averaging, maximum penalized likelihood and Bayesian estimation for improving Gaussian mixture probability density estimates

IEEE Transactions on Neural Networks
Self-organizing mixture networks for probability density estimation

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a novel real-time approach to synthesizing 3D character animations of required style by adjusting a few parameters or scratching mouse cursor. Our approach regards learning captured 3D human motions as parametric Gaussians by the self-organizing mixture network (SOMN). The learned model describes motions under the control of a vector variable called the style variable, and acts as a probabilistic mapping from the low-dimensional style values to high-dimensional 3D poses. We have designed a pose synthesis algorithm and developed a user friendly graphical interface to allow the users, especially animators, to easily generate poses by giving style values. We have also designed a style-interpolation method, which accepts a sparse sequence of key style values and interpolates it and generates a dense sequence of style values for synthesizing a segment of animation. This key-styling method is able to produce animations that are more realistic and natural-looking than those synthesized by the traditional key-framing technique.