This paper is a report on the 3D Shape Retrieval Constest 2010 (SHREC'10) track on large scale retrieval. This benchmark allows evaluating how wel retrieval algorithms scale up to large collections of 3D models. The task was to perform 40 queries in a dataset of 10000 shapes. We describe the methods used and discuss the results and signifiance analysis. Categories and Subject Descriptors (according to ACM CCS): I.5.4 [Pattern Recognition]: Applications--Computer vision; H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval--Clustering; Experimentation; Performance
Remco C. Veltkamp, Geert-Jan Giezeman, Hannah Bast