Large-Scale 3D Shape Retrieval from ShapeNet Core55
Loading...
Date
2016
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
With the advent of commodity 3D capturing devices and better 3D modeling tools, 3D shape content is becoming increasingly prevalent. Therefore, the need for shape retrieval algorithms to handle large-scale shape repositories is more and more important. This track aims to provide a benchmark to evaluate large-scale shape retrieval based on the ShapeNet dataset. We use ShapeNet Core55, which provides more than 50 thousands models over 55 common categories in total for training and evaluating several algorithms. Five participating teams have submitted a variety of retrieval methods which were evaluated on several standard information retrieval performance metrics. We find the submitted methods work reasonably well on the track benchmark, but we also see significant space for improvement by future algorithms. We release all the data, results, and evaluation code for the benefit of the community.
Description
@inproceedings{10.2312:3dor.20161092,
booktitle = {Eurographics Workshop on 3D Object Retrieval},
editor = {A. Ferreira and A. Giachetti and D. Giorgi},
title = {{Large-Scale 3D Shape Retrieval from ShapeNet Core55}},
author = {Savva, M. and Yu, F. and Fish, N. and Han, J. and Kalogerakis, E. and Learned-Miller, E. G. and Li, Y. and Liao, M. and Maji, S. and Tatsuma, A. and Wang, Y. and Zhang, N. and Su, Hao and Zhou, Z. and Aono, M. and Chen, B. and Cohen-Or, D. and Deng, W. and Su, Hang and Bai, S. and Bai, X.},
year = {2016},
publisher = {The Eurographics Association},
ISSN = {1997-0471},
ISBN = {978-3-03868-004-8},
DOI = {10.2312/3dor.20161092}
}