Oriented Visibility for Multiview Reconstruction

  • V. Lempitsky
  • Y. Boykov
  • D. Ivanov
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3953)


Visibility estimation is arguably the most difficult problem in dense 3D reconstruction from multiple arbitrary views. In this paper, we propose a simple new approach to estimating visibility based on position and orientation of local surface patches. Using our concept of oriented visibility, we present a new algorithm for multiview reconstruction based on exact global optimization of surface photoconsistency using graph cuts on a CW-complex. In contrast to many previous methods for 3D reconstruction from arbitrary views, our method does not depend on initialization and is robust to photometrically difficult situations.


multiview reconstruction image-based modeling visibility dense stereo graph cuts directed graphs CW-complex global optimization 


  1. 1.
    Boykov, Y., Kolmogorov, V.: An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision. PAMI 26(9), 1124–1137 (2004)Google Scholar
  2. 2.
    Buehler, C., Gortler, S.J., Cohen, M., McMmillan, L.: Minimal Surfaces for Stereo Vision. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 885–899. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  3. 3.
    Culbertson, W., Malzbender, T., Slabaugh, G.: Generalized Voxel Coloring. In: Workshop on Vision Algorithms 1999, pp. 100–115 (1999)Google Scholar
  4. 4.
    Faugeras, O., Keriven, R.: Complete Dense Stereovision Using Level Set Methods. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 379–393. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  5. 5.
    Greig, D., Porteous, B., Seheult, A.: Exact maximum a posteriori estimation for binary images. Journal of the Royal Statistical Society 51(2), 271–279 (1989)Google Scholar
  6. 6.
    Kirsanov, D., Gortler, S.J.: A Discrete Global Minimization Algorithm for Continuous Variational Problems. Harvard CS Technical Report TR-14-04 (2004)Google Scholar
  7. 7.
    Kutulakos, K.N., Seitz, S.M.: A Theory of Shape by Space Carving. IJCV 2000, 38 (3), 199–218 (2000)Google Scholar
  8. 8.
    Middlebury Stereo Vision Page,
  9. 9.
    Kolmogorov, V., Zabih, R.: Multi-camera Scene Reconstruction via Graph Cuts. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 82–96. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  10. 10.
    Kolmogorov, V., Zabih, R.: What Energy Functions Can Be Minimized via Graph Cuts? In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 65–81. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  11. 11.
    Paris, S., Sillion, F., Quan, L.: A Surface Reconstruction Method Using Global Graph Cut Optimization. IJCV (to appear)Google Scholar
  12. 12.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of plausible Inference. Morgan Kaufmann, San Francisco (1988)Google Scholar
  13. 13.
    POV-Raytm raytracer,
  14. 14.
    Roy, S., Cox, I.: A maximum-flow formulation of the n-camera stereo correspondence problem. In: Proc. ICCV 1998, pp. 492–499 (1998)Google Scholar
  15. 15.
    Sinha, S., Pollefeys, M.: Multi-View Reconstruction Using Photo-consistency and Exact Silhouette Constraints: A Maximum-Flow Formulation. In: Proc. ICCV 2005, pp. 349–356 (2005)Google Scholar
  16. 16.
    Snow, D., Viola, P., Zabih, R.: Exact voxel occupancy with graph cuts. In: Proc. CVPR 2000, vol. 1, pp. 345–352 (2000)Google Scholar
  17. 17.
    Vogiatzis, G., Torr, P.H.S., Seitz, S., Cipolla, R.: Reconstructing Relief Surfaces. In: Proc. BMVC 2004, pp. 117–126 (2004)Google Scholar
  18. 18.
    Vogiatzis, G., Torr, P.H.S., Cipolla, R.: Multi-view stereo via Volumetric Graphcuts. In: Proc. CVPR 2005, pp. 391–398 (2005)Google Scholar
  19. 19.
    Wainwright, M.J., Jaakkola, T.S., Willsky, A.: MAP estimation via agreement on trees: Message-passing and linear programming. IEEE Trans. on Information Theory 51(11) (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • V. Lempitsky
    • 1
  • Y. Boykov
    • 2
  • D. Ivanov
    • 1
  1. 1.Department of MathematicsMoscow State UniversityMoscowRussia
  2. 2.Department of Computer ScienceThe University of Western OntarioLondonCanada

Personalised recommendations