Dense Non-rigid Surface Registration Using High-Order Graph Matching and Quasi-Conformal Geometry
Speaker:Prof. Dimitris Samaras
Department of Computer Science
Stony Brook University
Date & Time:14 Jan 2013 (Monday) 14:30
Venue:U102
Organized by:Department of Mathematics

Abstract

I will present our most recent techniques for non-rigid surface matching and tracking combining quasi-conformal mappings with efficient global optimization methods. I will first describe a high-order graph matching formulation to address non-rigid surface matching. The singleton terms capture the geometric and appearance similarities (e.g., curvature and texture) while the high-order terms model the intrinsic embedding energy. The method includes: 1) casting 3D surface registration into a graph matching problem that combines both geometric and appearance similarities and intrinsic embedding information, 2) the first implementation of high-order graph matching algorithm that solves a non-convex optimization problem, and 3) an efficient two-stage optimization approach to constrain the search space for dense surface registration. Furthermore by considering the set of all possible 3D surface matchings defined by specifying triplets of correspondences in the uniformization domain, we introduce a new matching cost between two 3D surfaces, which can be efficiently computed for surface tracking applications. Our method is validated through a series of experiments demonstrating its accuracy and efficiency, notably in challenging cases of large and/or non-isometric deformations, or meshes that are partially occluded, as well as dense, anisometric 3D surface tracking experiments.

Biography

Prof. Dimitris Samaras received his PhD in 2001 from the University of Pennsylvania. Since 2000, he has been teaching in the State University of New York at Stony Brook, where he is an associate professor and the director of the Image Analysis Laboratory. Since 2012 he is also the DIGITEO Chair in Ecole Centrale de Paris. His research interests include, the study of illumination in images, deformable models, face recognition, tracking and analysis of facial expression, categorical object recognition in human and computer vision, and statistical methods for the analysis of functional brain imaging data. He is an author of over 75 articles in top Computer Vision, Graphics and Machine Learning venues.