SHREC'10 track: correspondence finding

Alexander Bronstein (1) , Michael Bronstein (1) , Umberto Castellani (2) , Anastasia Dubrovina (3) , Leonidas Guibas (4) , Radu Horaud (5) , Ron Kimmel (1) , David Knossow (5) , Etienne von Lavante (5, 6) , Diana Mateus (5) , Maks Ovsjanikov (7) , Avinash Sharma (5)

1 Department of Computer Science [Haifa]
2 UNIVR | DI - Department of Computer Science [Verona]
3 EE-Technion - Department of Electrical Engineering - Technion [Haïfa]
4 Computer Science Department [Stanford]
5 PERCEPTION - Interpretation and Modelling of Images and Videos
6 Robotics Research Group
7 Geometric Computation Group [Stanford]

The SHREC'10 correspondence finding benchmark simulates a one-to-one shape matching scenario, in which one of the shapes undergoes multiple modifications and transformations. The benchmark allows evaluating how correspondence algorithms cope with certain classes of transformations and what is the strength of the transformations that can be dealt with. The present paper is a report of the 3D Shape Retrieval Contest 2010 (SHREC'10) correspondence finding benchmark results.

Domaines: Synthèse d'image et réalité virtuelle [cs.GR]

Alexander Bronstein, Michael Bronstein, Umberto Castellani, Anastasia Dubrovina, Leonidas Guibas, et al.. SHREC'10 track: correspondence finding. 3DOR2010 - Eurographics Workshop on 3D Object Retrieval, May 2010, Norrköping, Sweden. pp.87-91, ⟨10.2312/3DOR/3DOR10/087-091⟩. ⟨inria-00590262⟩