Shape Retrieval of Non-Rigid 3D Human Models

Published

April 26, 2016

Author(s)

Afzal A. Godil, David Pickup

Abstract

3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models. This benchmark provided a far stricter challenge than previous shape benchmarks. Here we extend the existing human model dataset with 145 new models for use as a separate training set, in order to standardise the training data used and provide a fairer comparison. All participants of the previous benchmark study have taken part in the new tests reported here, many providing up- dated results using our new data. In addition, further participants have also taken part, and we provide extra analysis of the retrieval results. A total of 25 different shape retrieval methods are compared.

Citation

International Journal of Computer Vision

Pub Type

Journals

Download Paper

Local Download

Keywords

3D Humans, Shape Retrieval, Non-Rigid Shape

Citation

Godil, A. and Pickup, D. (2016), Shape Retrieval of Non-Rigid 3D Human Models, International Journal of Computer Vision, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=918378 (Accessed May 22, 2025)