Intrinsic Dense 3D Surface Tracking

This paper presents a novel intrinsic 3D surface distance and its use in a complete probabilistic tracking framework for dynamic 3D data. Registering two frames of a deforming 3D shape relies on accurate correspondences between all points across the two frames. In the general case such correspondence search is computationally intractable. Common prior assumptions on the nature of the deformation such as near-rigidity, isometry or learning from a training set, reduce the search space but often at the price of loss of accuracy when it comes to deformations not in the prior assumptions. If we consider the set of all possible 3D surface matchings defined by specifying triplets of correspondences in the uniformization domain, then we introduce a new matching cost between two 3D surfaces. The lowest feature differences across this set of matchings that cause two points to correspond, become the matching cost of that particular correspondence. We show that for surface tracking applications,...

• Type: Journal
• Year: 2011
• Where: CVPR
• Authors: Yun Zeng, Chaohui Wang, Yang Wang, David Gu, Dimitris Samaras, Nikos Paragios
• Keywords: Computer Vision, CVPR 2011, Intrinsic 3D Surface, Matching Cost, Uniformization Domain