Dynamic Coupled Component Analysis

 (with Michael J. Black,  Computer Science Department. Brown University. USA)



ABSTRACT: We present a method for simultaneously learning linear models of multiple high dimensional data sets and the dependencies

between them.For example, we learn asymmetrically coupled linear models for the faces of two different people and show how these models

can be used to animate one face given a video sequence of the other. We pose the problem as a form of Asymmetric Coupled Component

Analysis (ACCA) in which we simultaneously learn the subspaces for reducing the dimensionality of each dataset while coupling the parameters

of the low dimensional representations. Additionally, a dynamic form of ACCA is proposed, that extends this work to model temporal

dependencies in the data sets. To account for outliers and missing data, we formulate the problem in a statistically robust estimation framework.

We review connections with previous work and illustrate the method with examples of synthesized dancing and the animation of facial avatars.








 De la Torre, F. and Black, M. J., Dynamic coupled component Analysis
 IEEE Proc. Computer Vision and Pattern Recognition, CVPR'01, Kauai, Hawaii, Vol. II, pp. 643-650, Dec. 2001.
 (postscript, 8.33 MB)(pdf, 0.43 MB), 



 De la Torre, F. and Black, M. J. Robust parameterized Component Analysis: Theory and applications to 2D Facial Appearance Models.
 Submitted to Computer Vision and Image Understanding.














Facial animation









Virtual animation