|
|
Invited Speakers
|
André Gagalowicz Projet MIRAGES INRIA - Rocquencourt Domaine de Voluceau Le Chesnay Cedex, France |
3D face tracking including non verbal expressions
We propose a new technique for 3D face tracking in video sequences, which works without markers and once initialized, doesn't require any further interaction. A specific geometric model of the face (in a neutral position, for example) is used as input as well as a realistic hierarchical face animation model.
The algorithm includes a new method for precise face expression tracking in a video sequence. It uses this hierarchical animation system built over a morphable polyhedral 3D face model. Its low level animation mechanism is based upon MPEG-4 specification which is implemented via local point-driven mesh deformations adapted to the face geometry. The set of MPEG-4 animation parameters is in its turn controlled by a higher level system based upon facial muscles structure. This allows to perform precise tracking of complicated non verbal facial expressions as well as to produce face-to-face retargeting by transmitting the expression parameters to different faces. We finally show how to obtain an automatic semantic interpretation of the expressions from the former tracking results.
| Dr. Nathan Griffiths |
Trust Mechanisms in MAS
More info to follow
