Abstract
We introduce an algorithm for unsupervised co-segmentation of a set of shapes so as to reveal the semantic shape parts and establish their correspondence across the set. The input set may exhibit significant shape variability where the shapes do not admit proper spatial alignment and the corresponding parts in any pair of shapes may be geometrically dissimilar. Our algorithm can handle such challenging input sets since, first, we perform co-analysis in a descriptor space, where a combination of shape descriptors relates the parts independently of their pose, location, and cardinality. Secondly, we exploit a key enabling feature of the input set, namely, dissimilar parts may be "linked" through third-parties present in the set. The links are derived from the pairwise similarities between the parts' descriptors. To reveal such linkages, which may manifest themselves as anisotropic and non-linear structures in the descriptor space, we perform spectral clustering with the aid of diffusion maps. We show that with our approach, we are able to co-segment sets of shapes that possess significant variability, achieving results that are close to those of a supervised approach.
Supplemental Material
Available for Download
- Biasotti, S., Giorgi, D., Spagnuolo, M., and Falcidieno, B. 2008. Reeb graphs for shape analysis and applications. Theoretical Computer Science 392, 1--3, 5--22. Google ScholarDigital Library
- Boykov, Y., Veksler, O., and Zabih, R. 2001. Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 11, 1222--1239. Google ScholarDigital Library
- Chen, X., Golovinskiy, A., and Funkhouser, T. 2009. A benchmark for 3D mesh segmentation. ACM Trans. on Graphics (Proc. SIGGRAPH) 28, 3, 1--12. Google ScholarDigital Library
- Coifman, R. R., and Lafon, S. 2006. Diffusion maps. Applied and Computational Harmonic Analysis 21, 1, 5--30.Google ScholarCross Ref
- Comaniciu, D., and Meer, P. 2002. Mean shift: a robust approach towards feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24, 5, 603--619. Google ScholarDigital Library
- de Goes, F., Goldenstein, S., and Velho, L. 2008. A hierarchical segmentation of articulated bodies. Computer Graphics Forum (Proc. SGP) 27, 5, 1349--1356. Google ScholarDigital Library
- Fu, H., Cohen-Or, D., Dror, G., and Sheffer, A. 2008. Upright orientation of man-made objects. ACM Trans. on Graphics (Proc. SIGGRAPH) 27, 3, 1--8. Google ScholarDigital Library
- Gal, R., Sorkine, O., Mitra, N. J., and Cohen-Or, D. 2009. iWIRES: an analyze-and-edit approach to shape manipulation. ACM Trans. on Graphics (Proc. SIGGRAPH) 28, 3, 1--10. Google ScholarDigital Library
- Golovinskiy, A., and Funkhouser, T. 2009. Consistent segmentation of 3D models. Computers & Graphics (Proc. of SMI) 33, 3, 262--269. Google ScholarDigital Library
- Huang, Q., Koltun, V., and Guibas, L. 2011. Joint shape segmentation with linear programming. ACM Trans. on Graphics (Proc. SIGGRAPH Asia) 30, 6. Google ScholarDigital Library
- Joulin, A., Bach, F., and J. Ponce. 2010. Discriminative clustering for image co-segmentation. In Proc. IEEE Conf. on CVPR, 1943--1950.Google Scholar
- Kalogerakis, E., Hertzmann, A., and Singh, K. 2010. Learning 3D mesh segmentation and labeling. ACM Trans. on Graphics (Proc. SIGGRAPH) 29, 3, 1--11. Google ScholarDigital Library
- Kazhdan, M., Funkhouser, T., and Rusinkiewicz, S. 2004. Shape matching and anisotropy. ACM Trans. on Graphics 23, 3, 623--629. Google ScholarDigital Library
- Mitra, N. J., Yang, Y.-L., Yan, D.-M., Li, W., and Agrawala, M. 2010. Illustrating how mechanical assemblies work. ACM Trans. on Graphics (Proc. SIGGRAPH) 29, 4, 1--12. Google ScholarDigital Library
- Nadler, B., Lafon, S., Coifman, R. R., and Kevrekidis, I. G. 2005. Diffusion maps, spectral clustering and eigenfunctions of Fokker-Planck operators. In NIPS, 1--8.Google Scholar
- Rother, C., Kolmogorov, V., Minka, T., and Blake, A. 2006. Cosegmentation of image pairs by histogram matching -- incorporating a global constraint into MRFs. In Proc. IEEE Conf. on CVPR, 993--1000. Google ScholarDigital Library
- Shamir, A., Shapira, L., and Cohen-Or, D. 2006. Mesh analysis using geodesic mean-shift. The Visual Computer 22, 99--108. Google ScholarDigital Library
- Shamir, A. 2008. A survey on mesh segmentation techniques. Computer Graphics Forum 27, 6, 1539--1556.Google ScholarCross Ref
- Shapira, L., Shalom, S., Shamir, A., Cohen-Or, D., and Zhang, H. 2009. Contextual part analogies in 3D objects. Int. J. Comput. Vision 89, 2--3, 309--326. Google ScholarDigital Library
- Simari, P., Nowrouzezahrai, D., Kalogerakis, E., and Singh, K. 2009. Multi-objective shape segmentation and labeling. Computer Graphics Forum (Proc. SGP) 28, 5, 1415--1425. Google ScholarDigital Library
- van Kaick, O., Zhang, H., Hamarneh, G., and Cohen-Or, D. 2010. A survey on shape correspondence. In Proc. Eurographics State-of-the-Art Report, 1--23.Google Scholar
- van Kaick, O., Tagliasacchi, A., Sidi, O., Zhang, H., Cohen-Or, D., Wolf, L., and Hamarneh, G. 2011. Prior knowledge for part correspondence. Computer Graphics Forum (Proc. EUROGRAPHICS) 30, 2, 553--562.Google ScholarCross Ref
- Wang, Y., Xu, K., Li, J., Zhang, H., Shamir, A., Liu, L., Cheng, Z., and Xiong, Y. 2011. Symmetry hierarchy of man-made objects. Computer Graphics Forum (Proc. EUROGRAPHICS) 30, 2, 287--296.Google ScholarCross Ref
- Xu, W., Wang, J., Yin, K., Zhou, K., van de Panne, M., Chen, F., and Guo, B. 2009. Joint-aware manipulation of deformable models. ACM Trans. on Graphics (Proc. SIGGRAPH) 28, 3, 1--9. Google ScholarDigital Library
- Xu, K., Li, H., Zhang, H., Cohen-Or, D., Xiong, Y., and Cheng, Z. 2010. Style-content separation by anisotropic part scales. ACM Trans. on Graphics (Proc. SIGGRAPH Asia) 29, 5, 1--9. Google ScholarDigital Library
- Zhang, H., van Kaick, O., and Dyer, R. 2010. Spectral mesh processing. Computer Graphics Forum 29, 6, 1865--1894.Google ScholarCross Ref
Index Terms
- Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering
Recommendations
Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering
SA '11: Proceedings of the 2011 SIGGRAPH Asia ConferenceWe introduce an algorithm for unsupervised co-segmentation of a set of shapes so as to reveal the semantic shape parts and establish their correspondence across the set. The input set may exhibit significant shape variability where the shapes do not ...
Deformation-driven shape correspondence via shape recognition
Many approaches to shape comparison and recognition start by establishing a shape correspondence. We "turn the table" and show that quality shape correspondences can be obtained by performing many shape recognition tasks. What is more, the method we ...
Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization
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 ...
Comments