Supervised Descriptor Learning for Non-Rigid Shape Matching

  • Étienne Corman
  • Maks OvsjanikovEmail author
  • Antonin Chambolle
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8928)


We present a novel method for computing correspondences between pairs of non-rigid shapes. Unlike the majority of existing techniques that assume a deformation model, such as intrinsic isometries, a priori and use a pre-defined set of point or part descriptors, we consider the problem of learning a correspondence model given a collection of reference pairs with known mappings between them. Our formulation is purely intrinsic and does not rely on a consistent parametrization or spatial positions of vertices on the shapes. Instead, we consider the problem of finding the optimal set of descriptors that can be jointly used to reproduce the given reference maps. We show how this problem can be formalized and solved for efficiently by using the recently proposed functional maps framework. Moreover, we demonstrate how to extract the functional subspaces that can be mapped reliably across shapes. This gives us a way to not only obtain better functional correspondences, but also to associate a confidence value to the different parts of the mappings. We demonstrate the efficiency and usefulness of the proposedapproach on a variety of challenging shape matching tasks.


Shape matching Correspondences Feature learning 


  1. 1.
    Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: Scape: shape completion and animation of people. In: ACM Transactions on Graphics (TOG) 24, pp. 408–416. ACM (2005)Google Scholar
  2. 2.
    Aubry, M., Schlickewei, U., Cremers, D.: The wave kernel signature: A quantum mechanical approach to shape analysis. In: Computer Vision Workshops (ICCV Workshops), pp. 1626–1633. IEEE (2011)Google Scholar
  3. 3.
    Azencot, O., Ben-Chen, M., Chazal, F., Ovsjanikov, M.: An operator approach to tangent vector field processing. Computer Graphics Forum 32(5), 73–82 (2013)CrossRefGoogle Scholar
  4. 4.
    Bookstein, F.L.: Landmark methods for forms without landmarks: morphometrics of group differences in outline shape. Medical image analysis 1(3), 225–243 (1997)CrossRefGoogle Scholar
  5. 5.
    Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Generalized multidimensional scaling: a framework for isometry-invariant partial surface matching. PNAS 103(5) (2006)Google Scholar
  6. 6.
    Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Numerical geometry of non-rigid shapes. Springer (2008)Google Scholar
  7. 7.
    Chen, X., Saparov, A., Pang, B., Funkhouser, T.: Schelling points on 3d surface meshes. ACM Trans. Graph. (TOG) 31(4), 29 (2012)CrossRefzbMATHGoogle Scholar
  8. 8.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Training models of shape from sets of examples. In: BMVC 1992, pp. 9–18 (1992)Google Scholar
  9. 9.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models-their training and application. Computer Vision and Image Understanding 61(1), 38–59 (1995)CrossRefGoogle Scholar
  10. 10.
    Dryden, I.L., Mardia, K.V.: Statistical shape analysis, vol. 4. John Wiley & Sons, New York (1998)zbMATHGoogle Scholar
  11. 11.
    Gao, X., Su, Y., Li, X., Tao, D.: A review of active appearance models. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews 40(2), 145–158 (2010)CrossRefGoogle Scholar
  12. 12.
    Hasler, N., Stoll, C., Sunkel, M., Rosenhahn, B., Seidel, H.P.: A statistical model of human pose and body shape. In: Computer Graphics Forum 28, pp. 337–346. Wiley Online Library (2009)Google Scholar
  13. 13.
    Huang, Q.X., Adams, B., Wicke, M., Guibas, L.J.: Non-rigid registration under isometric deformations. CGF (Proc. SGP) 27(5), 1449–1457 (2008)Google Scholar
  14. 14.
    Huang, Q., Wang, F., Guibas, L.: Functional map networks for analyzing and exploring large shape collections. ACM Trans. Graph. 33(4), 36:1–36:11 (2014)Google Scholar
  15. 15.
    Kalogerakis, E., Hertzmann, A., Singh, K.: Learning 3d mesh segmentation and labeling. ACM Trans. Graph. 29(4), 102 (2010)CrossRefGoogle Scholar
  16. 16.
    Kilian, M., Mitra, N.J., Pottmann, H.: Geometric modeling in shape space. ACM Transactions on Graphics (TOG) 26, 64 (2007)CrossRefGoogle Scholar
  17. 17.
    Kim, V.G., Lipman, Y., Funkhouser, T.: Blended intrinsic maps. ACM TOG (Proc. SIGGRAPH) 30(4) (2011)Google Scholar
  18. 18.
    Lee, C.H., Varshney, A., Jacobs, D.W.: Mesh saliency. In: ACM Transactions on Graphics (TOG) 24, pp. 659–666. ACM (2005)Google Scholar
  19. 19.
    Lipman, Y., Funkhouser, T.: Mobius voting for surface correspondence. ACM Transactions on Graphics (Proc. SIGGRAPH) 28(3), August 2009Google Scholar
  20. 20.
    Litman, R., Bronstein, A.: Learning spectral descriptors for deformable shape correspondence (2013)Google Scholar
  21. 21.
    Mémoli, F.: On the use of gromov-hausdorff distances for shape comparison. In: Symposium on Point Based Graphics, pp. 81–90 (2007)Google Scholar
  22. 22.
    Ovsjanikov, M., Ben-Chen, M., Solomon, J., Butscher, A., Guibas, L.: Functional maps: a flexible representation of maps between shapes. ACM Trans. Graph. 31(4), 30:1–30:11 (2012). CrossRefGoogle Scholar
  23. 23.
    Ovsjanikov, M., Mérigot, Q., Mémoli, F., Guibas, L.: One point isometric matching with the heat kernel. CGF 29(5), 1555–1564 (2010)Google Scholar
  24. 24.
    Ovsjanikov, M., Mérigot, Q., Pătrăucean, V., Guibas, L.: Shape matching via quotient spaces. Computer Graphics Forum 32(5), 1–11 (2013)CrossRefGoogle Scholar
  25. 25.
    Papadopoulo, T., Lourakis, M.I.A.: Estimating the jacobian of the singular value decomposition: Theory and applications. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 554–570. Springer, Heidelberg (2000) CrossRefGoogle Scholar
  26. 26.
    Rodolà, E., Bulò, S.R., Windheuser, T., Vestner, M., Cremers, D.: Dense non-rigid shape correspondence using random forests. In: Proc. CVPR (2014)Google Scholar
  27. 27.
    Rustamov, R.M., Ovsjanikov, M., Azencot, O., Ben-Chen, M., Chazal, F., Guibas, L.: Map-based exploration of intrinsic shape differences and variability. ACM Transactions on Graphics (TOG) 32(4), 72 (2013)CrossRefGoogle Scholar
  28. 28.
    Sahillioğlu, Y., Yemez, Y.: Coarse-to-fine combinatorial matching for dense isometric shape correspondence. Computer Graphics Forum 30(5), 1461–1470 (2011)CrossRefGoogle Scholar
  29. 29.
    Shapira, N., Ben-Chen, M.: Cross-collection map inference by intrinsic alignment of shape spaces. In: Computer Graphics Forum. Wiley Online Library (2014)Google Scholar
  30. 30.
    Sumner, R.W., Zwicker, M., Gotsman, C., Popović, J.: Mesh-based inverse kinematics. In: ACM SIGGRAPH, pp. 488–495 (2005)Google Scholar
  31. 31.
    Sun, J., Ovsjanikov, M., Guibas, L.: A concise and provably informative multi-scale signature based on heat diffusion. In: Computer Graphics Forum 28, pp. 1383–1392. Wiley Online Library (2009)Google Scholar
  32. 32.
    Tam, G.K., Cheng, Z.Q., Lai, Y.K., Langbein, F.C., Liu, Y., Marshall, D., Martin, R.R., Sun, X.F., Rosin, P.L.: Registration of 3d point clouds and meshes: A survey from rigid to nonrigid. IEEE Transactions on Visualization and Computer Graphics 19(7), 1199–1217 (2013)CrossRefGoogle Scholar
  33. 33.
    Tevs, A., Bokeloh, M., Wand, M., Schilling, A., Seidel, H.P.: Isometric registration of ambiguous and partial data. In: Proc. CVPR, pp. 1185–1192 (2009)Google Scholar
  34. 34.
    Van Kaick, O., Tagliasacchi, A., Sidi, O., Zhang, H., Cohen-Or, D., Wolf, L., Hamarneh, G.: Prior knowledge for part correspondence. Computer Graphics Forum (Proc. Eurographics) 30(2), 553–562 (2011)CrossRefGoogle Scholar
  35. 35.
    Van Kaick, O., Zhang, H., Hamarneh, G., Cohen-Or, D.: A survey on shape correspondence. Computer Graphics Forum 30(6), 1681–1707 (2011)CrossRefGoogle Scholar
  36. 36.
    Zhang, H., Sheffer, A., Cohen-Or, D., Zhou, Q., Van Kaick, O., Tagliasacchi, A.: Deformation-driven shape correspondence. In: Proc. SGP, pp. 1431–1439 (2008)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Étienne Corman
    • 1
    • 2
  • Maks Ovsjanikov
    • 1
    Email author
  • Antonin Chambolle
    • 2
  1. 1.LIXÉcole PolytechniquePalaiseauFrance
  2. 2.CMAPÉcole Polytechnique, CNRSPalaiseauFrance

Personalised recommendations