SHREC'10 Track: Feature Detection and Description
Alexander M. Bronstein, Michael M. Bronstein, Benjamín Bustos, Umberto Castellani, Crisani, M., Bianca Falcidieno, Leonidas Guibas, Iasonas Kokkinos, Vittorio Murino, Maks Ovsjanikov, Giuseppe Patanè, Ivan Sipiran, Michela Spagnuolo, Jian Zhong Sun · HAL (Le Centre pour la Communication Scientifique Directe) · 2010
Feature-based approaches have recently become very popular in computer vision and image analysis applications, and are becoming a promising direction in shape retrieval. The SHREC10 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 3D Shape Retrieval Contest 2010 (SHREC10) feature detection and description benchmark results.