Suivi volumétrique de formes 3D non rigides

Keywords :

• temporal alignment
• surface deformation
• mesh tracking
• multiview video
• deformation model

In this thesis we propose algorithms for tracking 3D deformable shapes in motion from multiview video. Although series of reconstructed 3D shapes can be obtained by applying a static reconstruction algorithm to each temporal frame independently, such series do not represent motion. Instead, we want to provide a temporally coherent representation of the sequence of shapes resulting from temporal evolutions of a shape. Precisely, we want to represent the observed shape sequence as a 3D surface mesh whose vertices move in time but whose topology is constant.
In contrast with most existing approaches, we propose to represent the motion of inner shape volumes, with the aim of better accounting for the volumetric nature of the observed object. We provide a fully volumetric approach to the fundamental problems of deformable shape tracking, which are the association between corresponding shape elements and the deformation model. In particular, we extend to a volumetric shape representation the EM-ICP tracking framework and the association-by-detection strategy.
Furthermore, in order to better constrain the shape tracking problem, we propose a model for the temporal evolution of deformation. Our deformation model defines a shape space parametrized by variables that capture local deformation properties of the shape and whose values are automatically learned during the tracking process.
We validate our tracking algorithms on several multiview video sequences with ground truth (silhouette and marker-based tracking). Our results are better or comparable to state of the art approaches.
Finally, we show that volumetric tracking and the shape representation we choose can be leveraged for producing shape animations which combine captured and simulated motion.

President:

Mr Adrien Bartoli (Professeur - Université d'Auvergne)

Directors:

• Mr Jean Sebastien Franco (Maître de Conférence - Grenoble INP )
• Mr Edmond Boyer (Directeur de recherche - Inria Grenoble Rhône-Alpes )

Raporteurs:

• Mme Lourdes Agapito (Professeur - University College London )
• Mr Michael M. Bronstein (Professeur - Università della Svizzera Italiana )