Applying Random Forests to the Problem of Dense Non-rigid Shape Correspondence

  • Matthias VestnerEmail author
  • Emanuele Rodolà
  • Thomas Windheuser
  • Samuel Rota Bulò
  • Daniel Cremers
Conference paper
Part of the Mathematics and Visualization book series (MATHVISUAL)


We introduce a novel dense shape matching method for deformable, three-dimensional shapes. Differently from most existing techniques, our approach is general in that it allows the shapes to undergo deformations that are far from being isometric. We do this in a supervised learning framework which makes use of training data as represented by a small set of example shapes. From this set, we learn an implicit representation of a shape descriptor capturing the variability of the deformations in the given class. The learning paradigm we choose for this task is a random forest classifier. With the additional help of a spatial regularizer, the proposed method achieves significant improvements over the baseline approach and obtains state-of-the-art results while keeping a low computational cost.


Random Forest Shape Descriptor Split Function Shape Match Random Forest Classifier 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  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), vol. 24, pp. 408–416. ACM, New York (2005)Google Scholar
  2. 2.
    Aubry, M., Schlickewei, U., Cremers, D.: The wave kernel signature: a quantum mechanical approach to shape analysis. In: ICCV Workshops, Barcelona (2011)Google Scholar
  3. 3.
    Breiman, L.: Random forests. In: Machine Learning, vol. 45. Springer, Berlin/Heidelberg (2001)Google Scholar
  4. 4.
    Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Generalized multidimensional scaling: a framework for isometry-invariant partial surface matching. PNAS 103 (5), 1168–1172 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Numerical Geometry of Non-Rigid Shapes. Springer, New York (2008). Incorporated, 1 editionGoogle Scholar
  6. 6.
    Corman, É., Ovsjanikov, M., Chambolle, A.: Supervised descriptor learning for non-rigid shape matching. In: European Conference on Computer Vision, pp 283–298 (2014)Google Scholar
  7. 7.
    Criminisi, A., Shotton, J., Konukoglu, E.: Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-supervised Learning. Foundations and Trends in Computer Graphics and Vision. Now, Boston (2012)zbMATHGoogle Scholar
  8. 8.
    Fanelli, G., Gall, J., Van Gool, L.: Real time head pose estimation with random regression forests. In: CVPR, Colorado Springs (2011)CrossRefGoogle Scholar
  9. 9.
    Gall, J., Yao, A., Razavi, N., Van Gool, L., Lempitsky, V.: Hough forests for object detection, tracking, and action recognition. PAMI 33 (11), 2188–2202 (2011)CrossRefGoogle Scholar
  10. 10.
    Kim, V.G., Lipman, Y., Funkhouser, T.: Blended intrinsic maps. In: SIGGRAPH 2011, Vancouver (2011)Google Scholar
  11. 11.
    Kovnatsky, A., Bronstein, M.M., Bronstein, A.M., Glashoff, K., Kimmel, R.: Coupled quasi-harmonic bases. Comput. Graph. Forum 32 (2pt4), 439–448 (2013)Google Scholar
  12. 12.
    Litman, R., Bronstein, A.M.: Learning spectral descriptors for deformable shape correspondence. TPAMI 36 (1), 170–180 (2013)Google Scholar
  13. 13.
    Mémoli, F.: Gromov-Wasserstein distances and the metric approach to object matching. Found. Comput. Math. 11, 417–487 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Mémoli, F., Sapiro, G.: A theoretical and computational framework for isometry invariant recognition of point cloud data. Found. Comput. Math. 5 (3), 313–347 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Meyer, M., Desbrun, M., Schröder, P., Barr, A.H.: Discrete differential-geometry operators for triangulated 2-manifolds. In: Proceedings of VisMath, Berlin (2002)zbMATHGoogle Scholar
  16. 16.
    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)Google Scholar
  17. 17.
    Ovsjanikov, M., Mérigot, Q., Mémoli, F., Guibas, L.: One point isometric matching with the heat kernel. Comput. Graph. Forum 29 (5), 1555–1564 (2010)CrossRefGoogle Scholar
  18. 18.
    Ovsjanikov, M., Sun, J., Guibas, L.: Global intrinsic symmetries of shapes. In: Computer Graphics Forum, vol. 27, pp. 1341–1348. Wiley Online Library (2008)Google Scholar
  19. 19.
    Pickup, D., Sun, X., Rosin, P., Martin, R., Cheng, Z., Lian, Z., Aono, M., Ben Hamza, A., Bronstein, A., Bronstein, M., et al.: Shrec14 track: shape retrieval of non-rigid 3d human models. 3DOR 4 (7), 8 (2014)Google Scholar
  20. 20.
    Rodolà, E., Bronstein, A.M., Albarelli, A., Bergamasco, F., Torsello, A.: A game-theoretic approach to deformable shape matching. In: CVPR, Providence (2012)CrossRefGoogle Scholar
  21. 21.
    Rodolá, E., Rota Bulo, S., Windheuser, T., Vestner, M., Cremers, D.: Dense non-rigid shape correspondence using random forests. In: CVPR, Columbus, pp. 4177–4184 (2014)Google Scholar
  22. 22.
    Rodolà, E., Torsello, A., Harada, T., Kuniyoshi, T., Cremers, D.: Elastic net constraints for shape matching. In: ICCV, Sydney (2013)CrossRefGoogle Scholar
  23. 23.
    Rustamov, R.M.: Laplace-beltrami eigenfunctions for deformation invariant shape representation. In: SGP, Barcelona. Eurographics Association (2007)Google Scholar
  24. 24.
    Sahillioğlu, Y., Yemez, Y.: Coarse-to-fine combinatorial matching for dense isometric shape correspondence. Comput. Graph. Forum 30 (5), 1461–1470 (2011)CrossRefGoogle Scholar
  25. 25.
    Schölkopf, B., Steinke, F., Blanz, V.: Object correspondence as a machine learning problem. In: ICML, Bonn, pp. 776–783. ACM (2005)Google Scholar
  26. 26.
    Shotton, J., Johnson, M., Cipolla, R.: Semantic texton forests for image categorization and segmentation. In: CVPR, Anchorage (2008)CrossRefGoogle Scholar
  27. 27.
    Shtern, A., Kimmel, R.: Matching lbo eigenspace of non-rigid shapes via high order statistics. arXiv preprint arXiv:1310.4459 (2013)Google Scholar
  28. 28.
    Steinke, F., Blanz, V., Schölkopf, B.: Learning dense 3d correspondence. In: Advances in Neural Information Processing Systems, pp. 1313–1320. MIT Press, Cambridge/London (2006)Google Scholar
  29. 29.
    Sun, J., Ovsjanikov, M., Guibas, L.: A concise and provably informative multi-scale signature based on heat diffusion. In: SGP, Berlin. Eurographics Association (2009)Google Scholar
  30. 30.
    Taylor, J., Shotton, J., Sharp, T., Fitzgibbon, A.: The vitruvian manifold: inferring dense correspondences for one-shot human pose estimation. In: CVPR, Pittsburgh (2012)Google Scholar
  31. 31.
    Windheuser, T., Schlickewei, U., Schmidt, F.R., Cremers, D.: Geometrically consistent elastic matching of 3d shapes: a linear programming solution. In: ICCV, Barcelona (2011)Google Scholar
  32. 32.
    Windheuser, T., Vestner, M., Rodola, E., Triebel, R., Cremers, D.: Optimal intrinsic descriptors for non-rigid shape analysis. In: BMVC, Nottingham. BMVA Press (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Matthias Vestner
    • 1
    Email author
  • Emanuele Rodolà
    • 1
  • Thomas Windheuser
    • 1
  • Samuel Rota Bulò
    • 2
  • Daniel Cremers
    • 1
  1. 1.Technische Universität MünchenMunichGermany
  2. 2.Fondazione Bruno KesslerTrentoItaly

Personalised recommendations