Please use this identifier to cite or link to this item:
Title: Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization
Authors: Meng, Min
Xia, Jiazhi
Luo, Jun
He, Ying
Keywords: DRNTU::Engineering::Computer science and engineering
Issue Date: 2012
Source: Meng, M., Xia, J., Luo, J., & He, Y. (2013). Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization. Computer-Aided Design, 45(2), 312-320.
Series/Report no.: Computer-aided design
Abstract: This paper presents an unsupervised algorithm for co-segmentation of a set of 3D shapes of the same family. Taking the over-segmentation results as input, our approach clusters the primitive patches to generate an initial guess. Then, it iteratively builds a statistical model to describe each cluster of parts from the previous estimation, and employs the multi-label optimization to improve the co-segmentation results. In contrast to the existing “one-shot” algorithms, our method is superior in that it can improve the co-segmentation results automatically. The experimental results on the Princeton Segmentation Benchmark demonstrate that our approach is able to co-segment 3D shapes with significant variability and achieves comparable performance to the existing supervised algorithms and better performance than the unsupervised ones.
ISSN: 0010-4485
DOI: 10.1016/j.cad.2012.10.014
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Citations 5

Updated on Jul 13, 2020

Citations 5

Updated on Mar 6, 2021

Page view(s) 20

Updated on Jun 15, 2021

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.