SHREC 2011: robust feature detection and description benchmark

Edmond Boyer (1) , Alexander M. Bronstein (2) , Michael M. Bronstein (3) , Benjamin Bustos (4) , Tal Darom (5) , Radu Horaud (6) , Ingrid Hotz (7) , Yosi Keller (5) , Johannes Keustermans (8) , Artiom Kovnatsky (9) , Roee Litman (2) , Jan Reininghaus (7) , Ivan Sipiran (4) , Dirk Smeets (8) , Paul Suetens (8) , Dirk Vandermeulen (8) , Andrei Zaharescu (10) , Valentin Zobel (7)

1 MORPHEO - Capture and Analysis of Shapes in Motion
2 Department of Electrical Engineering
3 Faculty of Informatics [Lugano]
4 Universidad de Chile - Department of Computer Science
5 Faculty of Engineering
6 PERCEPTION - Interpretation and Modelling of Images and Videos
7 ZIB - Zuse Institute Berlin
8 ESAT/SCD-COSIC - Department of Electrical Engineering - K.U.Leuven
9 TECHNION - Department of Mathematics
10 Aimetis Corp.

Feature-based approaches have recently become very popular in computer vision and image analysis applications, and are becoming a promising direction in shape retrieval. SHREC'11 robust feature detection and description benchmark simulates the feature detection and description stages of feature-based shape retrieval algorithms. The benchmark tests the performance of shape feature detectors and descriptors under a wide variety of transformations. The benchmark allows evaluating how algorithms cope with certain classes of transformations and strength of the transformations that can be dealt with. The present paper is a report of the SHREC'11 robust feature detection and description benchmark results.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Edmond Boyer, Alexander M. Bronstein, Michael M. Bronstein, Benjamin Bustos, Tal Darom, et al.. SHREC 2011: robust feature detection and description benchmark. 3DOR2011 - Eurographics Workshop on 3D Object Retrieval, ACM Siggraph, Apr 2011, Llandudno, United Kingdom. pp.71-78, ⟨10.2312/3DOR/3DOR11/071-078⟩. ⟨hal-00752990⟩