Skip to main content Accessibility help

Partial Shape Matching Without Point-Wise Correspondence

  • Jonathan Pokrass (a1), Alexander M. Bronstein (a1) and Michael M. Bronstein (a2)


Partial similarity of shapes is a challenging problem arising in many important applications in computer vision, shape analysis, and graphics, e.g. When one has to deal with partial information and acquisition artifacts. The problem is especially hard when the underlying shapes are non-rigid and are given up to a deformation. Partial matching is usually approached by computing local descriptors on a pair of shapes and then establishing a point-wise non-bijective correspondence between the two, taking into account possibly different parts. In this paper, we introduce an alternative correspondence-less approach to matching fragments to an entire shape undergoing a non-rigid deformation. We use region-wise local descriptors and optimize over the integration domains on which the integral descriptors of the two parts match. The problem is regularized using the Mumford-Shah functional. We show an efficient discretization based on the Ambrosio-Tortorelli approximation generalized to triangular point clouds and meshes, and present experiments demonstrating the success of the proposed method.


Corresponding author

Corresponding author. Email address:
Corresponding author. Email address:
Corresponding author. Email address:


Hide All
[1] Aflalo, J., Bronstein, A. M., Bronstein, M. M., and Kimmel, R.. Deformable shape retrieval by learning diffusion kernels. In Proc. SSVM, 2011.
[2] Ambrosio, L. and Tortorelli, V.M.. Approximation of functionals depending on jumps by elliptic functionals via-convergence. Comm. Pure Appl. Math, 43(8):999–1036, 1990.
[3] Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., and Davis, J.. Scape: shape completion and animation of people. In Proceedings of the SIGGRAPH Conference, 2005.
[4] Aubry, M., Schlickewei, U., and Cremers, D.. The wave kernel signature: A quantum mechanical approach to shape analysis. In Proc. Workshop 4DMOD, 2011.
[5] Belkin, M. and Niyogi, P.. Towards a theoretical foundation for laplacian-based manifold methods. COLT, pages 486–500, 2005.
[6] Belkin, M., Sun, J., and Wang, Y.. Constructing laplace operator from point clouds in rd . In 20th ACM-SIAM Sympos. Discrete Algorithms, pages 1031–1040. ACM-SIAM, 2009.
[7] Besl, P. J. and McKay, N. D.. A method for registration of 3D shapes. Trans. PAMI, 14:239–256, 1992.
[8] Bronstein, A. M.. Spectral descriptors for deformable shapes. Technical Report arXiv:1110.5015v1, 2011.
[9] Bronstein, A. M. and Bronstein, M. M.. Not only size matters: regularized partial matching of nonrigid shapes. In Prof. NORDIA, 2008.
[10] Bronstein, A. M. and Bronstein, M. M.. Regularized partial matching of rigid shapes. In Proc. ECCV, pages 143–154, 2008.
[11] Bronstein, A. M., Bronstein, M. M., Carmon, Y., and Kimmel, R.. Partial similarity of shapes using a statistical significance measure. IPSJ Trans. Computer Vision and Applications, 1:105–114, 2009.
[12] Bronstein, A. M., Bronstein, M. M., Guibas, L. J., and Ovsjanikov, M.. Shape google: geometric words and expressions for invariant shape retrieval. ACM Transactions on Graphics (TOG), 30(1):1, 2011.
[13] Bronstein, A. M., Bronstein, M. M., and Kimmel, R.. Generalized multidimensional scaling: a framework for isometry-invariant partial surface matching. Proc. National Academy of Science (PNAS), 103(5):1168–1172, 2006.
[14] Bronstein, A. M., Bronstein, M. M., and Kimmel, R.. Robust expression-invariant face recognition from partially missing data. In Proc. European Conf. Computer Vision (ECCV), pages 396–408, 2006.
[15] Bronstein, A. M., Bronstein, M. M., and Kimmel, R.. Numerical geometry of non-rigid shapes. Springer-Verlag New York Inc, 2008.
[16] Bronstein, A.M., Bronstein, M.M., Carmon, Y., and Kimmel, R.. Partial similarity of shapes using a statistical significance measure. Trans. Computer Vision and Applications, 1(0):105–114, 2009.
[17] Bronstein, M. M. and Kokkinos, I.. Scale-invariant heat kernel signatures for non-rigid shape recognition. In Proc. CVPR, 2010.
[18] Luo, C., Sun, J., and Wang, Y. Integral estimation from point cloud in d-dimensional space: A geometric view.
[19] Chan, T. F. and Vese, L. A.. Active contours without edges. IEEE Trans. Image Processing, 10(2):266–277, 2001.
[20] Chen, Y. and Medioni, G.. Object modeling by registration of multiple range images. In Proc. Conf. Robotics and Automation, 1991.
[21] Clarenz, U., Rumpf, M., and Telea, A.. Robust feature detection and local classification for surfaces based on moment analysis. Trans. Visualization and Computer Graphics, 10(5):516–524, 2004.
[22] Domokos, C. and Kato, Z.. Affine Puzzle: Realigning Deformed Object Fragments without Correspondences. In Proc. ECCV, pages 777–790, 2010.
[23] Dutagaci, Helin, Godil, Afzal, Cheung, Chun Pan, Furuya, Takahiko, Hillenbrand, Ulrich, and Ohbuchi, Ryutarou. Shrec’10 track: Range scan retrieval. In 3DOR, pages 109–115, 2010.
[24] Gatzke, Timothy, Grimm, Cindy, Garland, Michael, and Zelinka, Steve. Curvature maps for local shape comparison. In In Shape Modeling International, pages 244–256, 2005.
[25] Gebal, K., Bærentzen, J.A., Aanæs, H., and Larsen, R.. Shape analysis using the auto diffusion function. In Computer Graphics Forum, volume 28, pages 1405–1413, 2009.
[26] Gromov, M.. Structures Métriques Pour les Variétés Riemanniennes. Number 1 in Textes Mathématiques. 1981.
[27] Har-Peled, S. and Varadarajan, K. R.. Projective clustering in high dimensions using core-sets. In 18th Annu. ACM Sympos. Comput. Geom., pages 312–318. ACM, 2002.
[28] Huang, Q.X., Flöry, S., Gelfand, N., Hofer, M., and Pottmann, H.. Reassembling fractured objects by geometric matching. ACM Trans. Graphics, 25(3):569–578, 2006.
[29] Jacobs, D., Weinshall, D., and Gdalyahu, Y.. Class representation and image retrieval with non-metric distances. Trans. PAMI, 22(6):583–600, 2000.
[30] Johnson, A. E. and Hebert, M.. Using spin images for efficient object recognition in cluttered 3D scenes. Trans. PAMI, 21(5):433–449, 1999.
[31] Jones, P. W., Maggioni, M., and Schul, R.. Manifold parametrizations by eigenfunctions of the Laplacian and heat kernels. PNAS, 105(6):1803, 2008.
[32] Kovnatsky, A., Bronstein, M. M., Bronstein, A. M., and Kimmel, R.. Photometric heat kernel signature. In Proc. Scale Space and Variational Methods (SSVM), 2011.
[33] Latecki, L. J., Lakaemper, R., and Wolter, D.. Optimal Partial Shape Similarity. Image and Vision Computing, 23:227–236, 2005.
[34] Lévy, B.. Laplace-Beltrami eigenfunctions towards an algorithm that “understands” geometry. In Proc. Shape Modeling and Applications, 2006.
[35] Luo, Chuanjiang, Safa, Issam, and Wang, Yusu. Approximating gradients for meshes and point clouds via diffusion metric. In Eurographics Symposium on Geometry Processing, 2009.
[36] Manay, S., Hong, B.W., Yezzi, A.J., and Soatto, S.. Integral invariant signatures. Lecture Notes in Computer Science, pages 87–99, 2004.
[37] Mémoli, F. and Sapiro, G.. A theoretical and computational framework for isometry invariant recognition of point cloud data. Foundations of Computational Mathematics, 5:313–346, 2005.
[38] Mitra, N. J., Guibas, L. J., Giesen, J., and Pauly, M.. Probabilistic fingerprints for shapes. In Proc. SGP, 2006.
[39] Mumford, D. and Shah, J.. Optimal approximations by piecewise smooth functions and associated variational problems. Communications on pure and applied mathematics, 42(5):577–685, 1989.
[40] Ovsjanikov, M., Bronstein, A.M., Guibas, L.J., and Bronstein, M.M.. Shape Google: a computer vision approach to invariant shape retrieval. In Proc. NORDIA. Citeseer, 2009.
[41] Pauly, M., Keiser, R., and Gross, M.. Multi-scale feature extraction on point-sampled surfaces. In Computer Graphics Forum, volume 22, pages 281289, 2003.
[42] Pokrass, J., Bronstein, A. M., and Bronstein, M. M.. A correspondence-less approach to matching of deformable shapes. In Proc. SSVM, 2011.
[43] Reuter, M., Wolter, F.-E., and Peinecke, N.. Laplace-spectra as fingerprints for shape matching. In Proc. ACM Symp. Solid and Physical Modeling, pages 101106, 2005.
[44] Rusu, Radu Bogdan, Blodow, Nico, and Beetz, Michael. Fast Point Feature Histograms (FPFH) for 3D Registration. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Kobe, Japan, May 12-17 2009.
[45] Sipiran, I. and Bustos, B.. A robust 3D interest points detector based on Harris operator. In Proc. 3DOR, pages 714. Eurographics, 2010.
[46] Sivic, J. and Zisserman, A.. Video Google: a text retrieval approach to object matching in videos. In Proc. CVPR, 2003.
[47] Strecha, C., Bronstein, A. M., Bronstein, M. M., and Fua, P.. LDAHash: improved matching with smaller descriptors. 35(1):6678, 2012.
[48] Sun, J., Ovsjanikov, M., and Guibas, L.. A Concise and Provably Informative Multi-Scale Signature Based on Heat Diffusion. In Computer Graphics Forum, volume 28, pages 13831392, 2009.
[49] Toldo, R., Castellani, U., and Fusiello, A.. Visual vocabulary signature for 3D object retrieval and partial matching. In Proc. 3DOR, 2009.
[50] Wahl, E., Hillenbrand, U., and Hirzinger, G.. Surflet-pair-relation histograms: A statistical 3d-shape representation for rapid classification. In 3DIM03, pages 474481, 2003.
[51] Zaharescu, A., Boyer, E., Varanasi, K., and R Horaud. Surface feature detection and description with applications to mesh matching. In Proc. CVPR, 2009.
[52] Zhang, C. and Chen, T.. Efficient feature extraction for 2D/3D objects in mesh representation. In Proc. ICIP, volume 3, 2001.


Partial Shape Matching Without Point-Wise Correspondence

  • Jonathan Pokrass (a1), Alexander M. Bronstein (a1) and Michael M. Bronstein (a2)


Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed