Isometric Registration of Ambiguous and Partial Data

This paper introduces a new shape matching algorithm for computing correspondences between 3D surfaces that have undergone (approximately) isometric deformations. The new approach makes two main contributions: First, the algorithm is, unlike previous work, robust to ``topological noise'' such as large holes or ``false connections'', which is both observed frequently in real-world scanner data. Second, our algorithm samples the space of feasible solutions such that uncertainty in matching can be detected explicitly. We employ a novel randomized feature matching algorithm in order to find robust subsets of geodesics to verify isometric consistency. The paper shows shape matching results for real world and synthetic data sets that could not be handled using previous deformable matching algorithms.

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Art Tevs (Max Planck Institute Informatik), Martin Bokeloh (University of Tubingen), Michael Wand (Saarland University & Max Planck Institut Informatik), Andreas Schilling (WSI/GRIS, University of Tuebingen), Hans-Peter Seidel (Max Planck Institut Informatik)
• Keywords: Computer Vision, CVPR 2009, Dense Features, Feature Matching, Point Cloud Matching, Ransac, Registration