Share Email Print

Proceedings Paper

Modeling heads from uncalibrated video sequences
Author(s): Pascal Fua
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We show that we can effectively fit a very complex facial animation model to uncalibrated video sequences, without benefit of targets, structured light or any other active device. Our approach is based on regularized bungle-adjustment followed by least-squares minimization using a set of progressively finer control triangulations. It takes advantage of three complementary sources of information: stereo data, silhouette edges and 2-D feature points. In this way, complete head models can be acquired with a cheap and entirely passive sensor, such as an ordinary video camera. They can then be fed to existing animation software to produce synthetic sequences.

Paper Details

Date Published: 14 December 1998
PDF: 12 pages
Proc. SPIE 3641, Videometrics VI, (14 December 1998); doi: 10.1117/12.333793
Show Author Affiliations
Pascal Fua, Swiss Federal Institute of Technology (Switzerland)

Published in SPIE Proceedings Vol. 3641:
Videometrics VI
Sabry F. El-Hakim; Armin Gruen, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?