research-article

Unsupervised Co-segmentation of 3D Shapes Based on Components

Authors:

Yunsheng KeAuthors Info & Claims

CSSE '19: Proceedings of the 2nd International Conference on Computer Science and Software Engineering

Pages 89 - 95

https://doi.org/10.1145/3339363.3339386

Published: 24 May 2019 Publication History

Abstract

The co-segmentation of a set of 3D shapes plays an important role in understanding and analyzing the 3D shapes. An unsupervised co-segmentation algorithm of 3D shapes based on components is proposed in view of the low efficiency and poor accuracy in the existing co-segmentation algorithms. Firstly, all the input models are pre-partitioned into meaningful components by calculating the conformal factor. Secondly, the 3D model is converted into a statistical model, and every column of the statistical model is used to represent different component unit, and then the corresponding relationship between different components is constructed and marked via Gaussian kernel function. Finally, dynamic k-means clustering algorithm is employed to realize meaningful co-segmentation. Experimental result demonstrates that the proposed algorithm can achieve co-segmentation of 3D model cluster with the same function but different postures and the obtained segmentation is convenient for further geometric analysis.

References

[1]

E. Zuckerberger, A. Tal, and S Shlafman, (2002) Polyhedral surface decomposition with applications, Computers & Graphics. 26(5), 733--743).

[2]

D. L. James and C. D. Twigg, (2005) Skinning mesh animations, ACM Transactions on Graphics. 24(3), 399--407.

Digital Library

[3]

P. R. Alface, F. Cayre, B. Macq, J. M. Francis, and H. Maître, (2003) Lapped spectral decomposition for 3D triangle mesh compression, Proceedings of Image Processing, Barcelona, Span, 781--784.

[4]

Y. Lipman, O. Sorkine, D. Cohen-Or, and A. Pasko, (2004) Differential coordinates for interactive mesh editing, Proceedings of Shape Modeling International, Genova, Italy, 181--190.

Digital Library

[5]

Q. Huang, V. Koltun, and L. Guibas, (2011) Joint shape segmentation with linear programming, ACM Transactions on Graphics. 30(6), 1--12.

Digital Library

[6]

O. Sidi, O. V. Kaick, Y. Kleiman, and D. Cohen-Or, (2011) Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering, ACM Transactions on Graphics. 30(6), 1--10.

Digital Library

[7]

H. B. Huang, E. Kalogerakis, and B. Marlin, (2015) Analysis and synthesis of 3D shape families via deep-learned generative models of surfaces, Computer Graphics Forum. 34(5), 25--38.

[8]

R. Hu, L. Fan, and L. Liu, (2012) Co-segmentation of 3d shapes via subspace clustering, Computer Graphics Forum. 31(5), 1703--1713.

Digital Library

[9]

A. Golovinskiy and T. Funkhouser, (2009) Consistent segmentation of 3D models, Computers & Graphics. 33(3), 262--269.

Digital Library

[10]

Y. Wang, S. Asafi, and O. V. Kaick, (2012) Active co-analysis of a set of shapes, ACM Transactions on Graphics. 31(6), 1--10.

Digital Library

[11]

Z. Xie, K. Xu, L. Liu, and B. Chen, (2014) 3D Shape Segmentation and Labeling via Extreme Learning Machine, Computer Graphics Forum. 33(5), 85--95.

Digital Library

[12]

V. K. Oliver, K. Xu, H. Zhang, Y. Wang, S. Sun, A. Shamir, and D. Cohen-Or, (2013) Co-hierarchical analysis of shape structures, ACM Transactions on Graphics. 32(4), 1--10.

Digital Library

[13]

Q. Huang, F. Wang, and L. Guibas, (2014) Functional map networks for analyzing and exploring large shape collections, ACM Transactions on Graphics. 33(4), 1--11.

Digital Library

[14]

Z. Shu, C. Qi, S. Xin, C. Hu, L. Wang, Y. Zhang, and J. Liu, (2016) Unsupervised 3D shape segmentation and co-segmentation via deep learning, Computer Aided Geometric Design. 43(2), 39--52.

Digital Library

[15]

M. Ben-Chen and C. Gotsman, (2008) Characterizing shape using conformal factors, Proceedings of 3D Object Retrieval, Eurographics Workshop, Crete, Greece, 1--8.

Digital Library

[16]

Y. Rubner, C. Tomasi, and L. J. Guibas, (2009) The earth mover's distance as a metric for image retrieval, International Journal of Computer Vision. 40(2), 99--121.

Digital Library

[17]

X. Chen, A. Golovinskiy, and T. Funkhouser, (2009) A benchmark for 3D mesh segmentation, ACM Transactions on Graphics. 28(3), 1--12.

Digital Library

[18]

Z. Wu, Y. Wang, R. Shou, B. Chen, and X. Liu, (2013) Unsupervised co-segmentation of 3D shapes via affinity aggregation spectral clustering, Computers & Graphics. 37(6), 628--637.

Digital Library

Cited By

Chowdhury PBhunia AGajjala VSain AXiang TSong Y(2022)Partially Does It: Towards Scene-Level FG-SBIR with Partial Input2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR52688.2022.00243(2385-2395)Online publication date: Jun-2022
https://doi.org/10.1109/CVPR52688.2022.00243

Index Terms

Unsupervised Co-segmentation of 3D Shapes Based on Components
1. Computing methodologies
  1. Computer graphics
    1. Shape modeling

Recommendations

Supervoxel-Based Segmentation of 3D Volumetric Images
Computer Vision – ACCV 2016
Abstract
While computer vision has made noticeable advances in the state of the art for 2D image segmentation, the same cannot be said for 3D volumetric datasets. In this work, we present a scalable approach to volumetric segmentation. The methodology, ...
Segmentation of CT Brain Images Using Unsupervised Clusterings

In this paper, we present non-identical unsupervised clustering techniques for the segmentation of CT brain images. Prior to segmentation, we enhance the visualization of the original image. Generally, for the presence of abnormal regions in the brain ...
Efficiently consistent affinity propagation for 3D shapes co-segmentation

Unsupervised co-segmentation for a set of 3D shapes is a challenging problem as no prior information is provided. The accuracy of the current approaches is necessarily restricted by the accuracy of the unsupervised face classification, which is used to ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

CSSE '19: Proceedings of the 2nd International Conference on Computer Science and Software Engineering

May 2019

202 pages

ISBN:9781450371728

DOI:10.1145/3339363

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

Research Center for Science and Technology for Learning, National Central University, Taiwan

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 24 May 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

The National Natural Science Foundation of China

Conference

CSSE 2019

CSSE 2019: 2019 2nd International Conference on Computer Science and Software Engineering

May 24 - 26, 2019

Xi'an, China

Acceptance Rates

CSSE '19 Paper Acceptance Rate 33 of 74 submissions, 45%;

Overall Acceptance Rate 33 of 74 submissions, 45%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
80
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 06 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Chowdhury PBhunia AGajjala VSain AXiang TSong Y(2022)Partially Does It: Towards Scene-Level FG-SBIR with Partial Input2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR52688.2022.00243(2385-2395)Online publication date: Jun-2022
https://doi.org/10.1109/CVPR52688.2022.00243

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents