Suivi de Surface par Déformations Itératives

In this paper we present a new method to capture the temporal evolution of a surface from multiple videos. By contrast to most current methods, our algorithm does not use any prior information on the nature of the tracked sur- face. In addition, it does not require sparse features to constrain the deformation but only relies on purely geo- metric information : a target set of 3D points and normals. Our approach is inspired by the Iterative Closest Point al- gorithm but handles large deformations of non-rigid sur- faces. To this aim, a mesh is iteratively deformed while enforcing local rigidity with respect to a reference model. This rigidity is preserved by diffusing it on local patches randomly seeded on the surface. The iterative nature of the algorithm combined with the softly enforced local rigi- dity allows to progressively evolve the mesh to fit the target data. The proposed method is validated and evaluated on several standard and challenging surface data sets acqui- red using real videos.