Graph-Based Range Image Registration Combining Geometric and Photometric Features

  • Ikuko Shimizu
  • Akihiro Sugimoto
  • Radim Šára
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4522)


We propose a coarse registration method of range images using both geometric and photometric features. The framework of existing methods using multiple features first defines a single similarity distance summing up each feature based evaluations, and then minimizes the distance between range images for registration. In contrast, we formulate registration as a graph-based optimization problem, where we independently evaluate geometric feature and photometric feature and consider only the order of point-to-point matching quality. We then find as large consistent matching as possible in the sense of the matching-quality order. This is solved as one global combinatorial optimization problem. Our method thus does not require any good initial estimation and, at the same time, guarantees that the global solution is achieved.


  1. 1.
    Besl, P.J., McKay, N.D.: A Method for Registration of 3-D Shapes. IEEE Trans. on PAMI 14(2), 239–256 (1992)Google Scholar
  2. 2.
    Chen, Y., Medioni, G.: Object Modeling by Registration of Multiple Range Images. IVC 10(3), 145–155 (1992)Google Scholar
  3. 3.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. John Willey and Sons, Inc., New York (2001)zbMATHGoogle Scholar
  4. 4.
    Feldmar, J., Ayache, N., Berring, F.: Rigid, Affine and Locally Affine Registration of Free-Form Surfaces. IJCV 18(2), 99–119 (1996)CrossRefGoogle Scholar
  5. 5.
    Godin, G., Laurendeau, D., Bergevin, R.: A Method for the Registration of Attributed Range Images. In: Proc. of 3DIM, pp. 179–186 (2001)Google Scholar
  6. 6.
    Guest, E., Berry, E., Baldock, R.A., Fidrich, M., Smith, M.A.: Robust Point Correspondence Applied to Two and Three-Dimensional Image Registration. IEEE Trans. on PAMI 23(2), 165–179 (2001)Google Scholar
  7. 7.
    Okatani, I.S., Sugimoto, A.: Registration of Range Images that Preserves Local Surface Structures and Color. In: Proc. 3DPVT, pp. 786–796 (2004)Google Scholar
  8. 8.
    Rusinkiewicz, S., Levoy, M.: Efficient Variants of the ICP Algorithm. In: Proc. of 3DIM, pp. 145–152 (2001)Google Scholar
  9. 9.
    Šára, R.: Finding the largest unambiguous component of stereo matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 900–914. Springer, Heidelberg (2002)Google Scholar
  10. 10.
    Šára, R.: Robust Correspondence Recognition for Computer Vision. In: Proc. of 17th ERS-IASC Symposium on Computational Statistics, pp. 119–131 (2006)Google Scholar
  11. 11.
    Šára, R., Okatani, I.S., Sugimoto, A.: Globally Convergent Range Image Registration by Graph Kernel Algorithm. In: Proc. of 3DIM, pp. 377–384 (2005)Google Scholar
  12. 12.
    Sharp, G.C., Lee, S.W., Wehe, D.K.: ICP Registration Using Invariant Features. IEEE Trans. on PAMI 24(1), 90–102 (2002)Google Scholar
  13. 13.
    Silva, L., Bellon, O.R.P., Boyer, K.L.: Enhanced, Robust Genetic Algorithms for Multiview Range Image Registration. In: Proc. of 3DIM, pp. 268–275 (2003)Google Scholar
  14. 14.
    Turk, G., Levoy, M.: Zipped Polygon Meshes from Range Images. In: ACM SIGGRAPH Computer Graphics, pp. 311–318 (1994)Google Scholar
  15. 15.
    Umeyama, S.: Least-Square Estimation of Transformation Parameters Between Two Point Patterns. IEEE Trans. on PAMI 13(4), 376–380 (1991)Google Scholar
  16. 16.
    Zhang, Z.: Iterative Point Matching for Registration of Free-Form Curves and Surfaces. IJCV 13(2), 119–152 (1994)CrossRefGoogle Scholar
  17. 17.
    Georgia Institute of Technology Large Geometric Models Archive,

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Ikuko Shimizu
    • 1
  • Akihiro Sugimoto
    • 2
  • Radim Šára
    • 3
  1. 1.Tokyo University of Agriculture and TechnologyJapan
  2. 2.National Institute of InformaticsJapan
  3. 3.Czech Technical UniversityCzech Republic

Personalised recommendations