Please use this identifier to cite or link to this item:
https://doi.org/10.1111/cgf.12243
Title: | Symmetry robust descriptor for non-rigid surface matching | Authors: | Zhang, Z. Yin, K. Foong, K.W.C. |
Issue Date: | Oct-2013 | Citation: | Zhang, Z., Yin, K., Foong, K.W.C. (2013-10). Symmetry robust descriptor for non-rigid surface matching. Computer Graphics Forum 32 (7) : 355-362. ScholarBank@NUS Repository. https://doi.org/10.1111/cgf.12243 | Abstract: | In this paper, we propose a novel shape descriptor that is robust in differentiating intrinsic symmetric points on geometric surfaces. Our motivation is that even the state-of-the-art shape descriptors and non-rigid surface matching algorithms suffer from symmetry flips. They cannot differentiate surface points that are symmetric or near symmetric. Hence a left hand of one human model may be matched to a right hand of another. Our Symmetry Robust Descriptor (SRD) is based on a signed angle field, which can be calculated from the gradient fields of the harmonic fields of two point pairs. Experiments show that the proposed shape descriptor SRD results in much less symmetry flips compared to alternative methods. We further incorporate SRD into a stand-alone algorithm to minimize symmetry flips in finding sparse shape correspondences. SRD can also be used to augment other modern non-rigid shape matching algorithms with ease to alleviate symmetry confusions. © 2013 The Eurographics Association and John Wiley & Sons Ltd. | Source Title: | Computer Graphics Forum | URI: | http://scholarbank.nus.edu.sg/handle/10635/79930 | ISSN: | 01677055 | DOI: | 10.1111/cgf.12243 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
SCOPUSTM
Citations
7
checked on Feb 22, 2021
WEB OF SCIENCETM
Citations
7
checked on Feb 22, 2021
Page view(s)
91
checked on Mar 1, 2021
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.