Shape-Based Retrieval of Articulated 3D Models Using Spectral Embedding

  • Varun Jain
  • Hao Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4077)


We present an approach for robust shape retrieval from data-bases containing articulated 3D shapes. We represent each shape by the eigenvectors of an appropriately defined affinity matrix, obtaining a spectral embedding. Retrieval is then performed on these embeddings using global shape descriptors. Transformation into the spectral domain normalizes the shapes against articulation (bending), rigid-body transformations, and uniform scaling. Experimentally, we show absolute improvement in retrieval performance when conventional shape descriptors are used in the spectral domain on the McGill database of articulated 3D shapes. We also propose a simple eigenvalue-based descriptor, which is easily computed and performs comparably against the best known shape descriptors applied to the original shapes.


Geodesic Distance Shape Descriptor Shape Retrieval Princeton Shape Benchmark Shape Database 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Shilane, P., Min, P., Kazhdan, M., Funkhouser, T.: The princeton shape benchmark. In: Proc. of Shape Modelling International (2004)Google Scholar
  2. 2.
    Chen, D.-Y., Tian, X.-P., Shen, Y.-T., Ouhyoung, M.: On visual similarity based 3d model retrieval. In: Computer Graphics Forum, pp. 223–232 (2003)Google Scholar
  3. 3.
    McGill 3D shape benchmark:
  4. 4.
    Tangelder, T., Veltkamp, R.: A survey of content based 3d shape retrieval methods. In: Proc. of Shape Modeling International, pp. 145–156 (2004)Google Scholar
  5. 5.
    Kazhdan, M., Funkhouser, T., Rusinkiewicz, S.: Rotation invariant spherical harmonic representation os 3d shape descriptors. In: Symposium on Geometry Processing (2003)Google Scholar
  6. 6.
    Fowlkes, C., Belongie, S., Chung, F., Malik, J.: Spectral grouping using the nyström method. IEEE Trans. on PAMI 26(2), 214–225 (2004)Google Scholar
  7. 7.
    Osada, R., Funkhouseri, T., Chazelle, B., Dobkin, D.: Matching 3d shapes with shape distribution. In: Proc. of Shape Modeling International, pp. 154–166 (2001)Google Scholar
  8. 8.
    Vranic, D.: An improvement of rotation invariant 3d shape descriptor based on functions on concentric spheres. In: Proc. of ICIP, pp. 757–760 (2003)Google Scholar
  9. 9.
    Shum, H.: On 3d shape similarity. In: Proc. of CVPR, pp. 526–531 (1996)Google Scholar
  10. 10.
    Kang, S., Ikeuchi, K.: Determining 3-d object pose using the complex extended gaussian image. In: Proc. of CVPR, pp. 580–585 (1991)Google Scholar
  11. 11.
    Kazhdan, M., Funkhouser, T., Rusinkiewicz, S.: Shape matching and anisotropy. ACM Trans. Graph. 23(3), 623–629 (2004)CrossRefGoogle Scholar
  12. 12.
    Ohbuchi, R., Minamitani, T., Takei, T.: Shape-similarity search of 3D models by using enhanced shape functions, pp. 97–104 (2003)Google Scholar
  13. 13.
    Hilaga, H., Shinagawa, Y., Kohmura, T., Kunii, T.K.: Topology matching for fully automatic similarity estimation of 3d shapes. In: SIGGRAPH, pp. 203–212 (2001)Google Scholar
  14. 14.
    Zhang, J., Siddiqi, K., Macrini, D., Shokoufandeh, A., Dickinson, A.: Retrieving articulated 3-d models using medial surfaces and their graph spectra. In: Rangarajan, A., Vemuri, B.C., Yuille, A.L. (eds.) EMMCVPR 2005. LNCS, vol. 3757, pp. 285–300. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  15. 15.
    Ng, A.Y., Jordan, M.I., Weiss, Y.: On spectral clustering: analysis and an algorithm. In: NIPS, pp. 857–864 (2002)Google Scholar
  16. 16.
    Zhang, H., Liu, R.: Mesh segmentation via recursive and visually salient spectral cuts. In: Proc. of Vision, Modeling, and Visualization, pp. 429–436 (2005)Google Scholar
  17. 17.
    Carcassoni, M., Hancock, E.R.: Spectral correspondence for point pattern matching. Pattern Recognition 36, 193–204 (2003)MATHCrossRefGoogle Scholar
  18. 18.
    Shapiro, L.S., Brady, J.M.: Feature based correspondence: an eigenvector approach. Image and Vision Computing 10(5), 283–288 (1992)CrossRefGoogle Scholar
  19. 19.
    Jain, V., Zhang, H.: Robust 3d shape correspondence in the spectral domain. In: Proc. of Shape Modeling International (to appear, 2006)Google Scholar
  20. 20.
    Elad, A., Kimmel, R.: On bending invariant signature of surfaces. IEEE Trans. on PAMI 25(10), 1285–1295 (2003)Google Scholar
  21. 21.
    Umeyama, S.: An eigen decomposition approach to weighted graph matching problem. IEEE Trans. on PAMI 10, 695–703 (1988)MATHGoogle Scholar
  22. 22.
    Scott, G., Longuet-Higgins, H.: An algorithm for associating the features of two patterns. Royal Soc. London B244 (1991)Google Scholar
  23. 23.
    Gotsman, C., Gu, X., Sheffer, A.: Fundamentals of spherical parameterization for 3d meshes. In: ACM Transactions on Graphics (Proceedings of SIGGRAPH) (2003)Google Scholar
  24. 24.
    Gotsman, C., Karni, Z.: Spectral compression of mesh geometry. In: Computer Graphics (Proceedings of SIGGRAPH), pp. 279–286 (2000)Google Scholar
  25. 25.
    Yang, L.: k-edge connected neighborhood graph for geodesic distance estimation and nonlinear data projection. In: Proc. of ICPR (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Varun Jain
    • 1
  • Hao Zhang
    • 1
  1. 1.GrUVi Lab, School of Computing SciencesSimon Fraser UniversityBurnaby, British ColumbiaCanada

Personalised recommendations