A comparison of methods for non-rigid 3D shape retrieval

Zhouhui Lian (1) , Afzal Godil (2) , Benjamin Bustos (3) , Mohamed Daoudi (4, 5) , Jeroen Hermans (6) , Shun Kawamura (7) , Yukinori Kurita (7) , Guillaume Lavoué (8) , Hien Van Nguyen (9) , Ryutarou Ohbuchi (7) , Yuki Ohkita (7) , Yuya Ohishi (7) , Fatih Porikli (10) , Martin Reuter (11) , Ivan Sipiran (3) , Dirk Smeets (6) , Paul Suetens (6) , Hedi Tabia (12) , Dirk Vandermeulen (6)

1 Institute of Computer Science and Technology
2 NIST - National Institute of Standards and Technology [Gaithersburg]
3 DCC - Computer Science Department [Santiago]
4 LIFL - FOX MIIRE
5 Institut TELECOM/TELECOM Lille1
6 KU Leuven - Catholic University of Leuven = Katholieke Universiteit Leuven
7 Yamanashi University
8 M2DisCo - Geometry Processing and Constrained Optimization
9 University of Maryland [College Park]
10 Mitsubishi Electric Research Laboratories, Cambridge, USA
11 Athinoula A. Martinos Center for Biomedical Imaging
12 MIDI - Multimedia Indexation and Data Integration

Non-rigid 3D shape retrieval has become an active and important research topic in content-based 3D object retrieval. The aim of this paper is to measure and compare the performance of state-of-the-art methods for non-rigid 3D shape retrieval. The paper develops a new benchmark consisting of 600 non- rigid 3D watertight meshes, which are equally classified into 30 categories, to carry out experiments for 11 different algorithms, whose retrieval accuracies are evaluated using six commonly utilized measures.

Mots clés: 3D shape retrieval; Non-rigid; Benchmark

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Recherche d'information [cs.IR]

Zhouhui Lian, Afzal Godil, Benjamin Bustos, Mohamed Daoudi, Jeroen Hermans, et al.. A comparison of methods for non-rigid 3D shape retrieval. Pattern Recognition, 2013, 46 (1), pp.449-461. ⟨10.1016/j.patcog.2012.07.014⟩. ⟨hal-00746279⟩