Advertisement

An Occupancy–Depth Generative Model of Multi-view Images

  • Pau Gargallo
  • Peter Sturm
  • Sergi Pujades
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4844)

Abstract

This paper presents an occupancy based generative model of stereo and multi-view stereo images. In this model, the space is divided into empty and occupied regions. The depth of a pixel is naturally determined from the occupancy as the depth of the first occupied point in its viewing ray. The color of a pixel corresponds to the color of this 3D point.

This model has two theoretical advantages. First, unlike other occupancy based models, it explicitly models the deterministic relationship between occupancy and depth and, thus, it correctly handles occlusions. Second, unlike depth based approaches, determining depth from the occupancy automatically ensures the coherence of the resulting depth maps.

Experimental results computing the MAP of the model using message passing techniques are presented to show the applicability of the model.

Keywords

Message Passing Single Pixel Factor Graph Visual Hull Likelihood Factor 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vision 47(1-3), 7–42 (2002)zbMATHCrossRefGoogle Scholar
  2. 2.
    Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: Computer Vision and Pattern Recognition 2006, Washington, DC, USA, pp. 519–528 (2006)Google Scholar
  3. 3.
    Strecha, C., Fransens, R., Gool, L.V.: Combined depth and outlier estimation in multi-view stereo. In: Computer Vision and Pattern Recognition 2006, Washington, pp. 2394–2401. IEEE Computer Society Press, Los Alamitos (2006)Google Scholar
  4. 4.
    Laurentini, A.: The visual hull concept for silhouette-based image understanding. IEEE Trans. Pattern Anal. Mach. Intell. 16(2), 150–162 (1994)CrossRefGoogle Scholar
  5. 5.
    Solem, J.E., Kahl, F., Heyden, A.: Visibility constrained surface evolution. In: Computer Vision and Pattern Recognition 2005, San Diego, USA, pp. 892–899 (2005)Google Scholar
  6. 6.
    Kang, S.B., Szeliski, R., Chai, J.: Handling occlusions in dense multi-view stereo. In: Computer Vision and Pattern Recognition 2001, Kauai, Hawaii, pp. 103–110 (2001)Google Scholar
  7. 7.
    Kolmogorov, V., Zabih, R.: Multi-camera scene reconstruction via graph cuts. In: European Conference on Computer Vision 2002, London, UK, pp. 82–96 (2002)Google Scholar
  8. 8.
    Gargallo, P., Sturm, P.: Bayesian 3d modeling from images using multiple depth maps. In: Computer Vision and Pattern Recognition 2005, San Diego, vol. 2, pp. 885–891 (2005)Google Scholar
  9. 9.
    Faugeras, O.D., Keriven, R.: Complete dense stereovision using level set methods. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 379–393. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  10. 10.
    Kutulakos, K.N., Seitz, S.M.: A theory of shape by space carving. Int. J. Comput. Vision 38(3), 199–218 (2000)zbMATHCrossRefGoogle Scholar
  11. 11.
    Paris, S., Sillion, F.X., Quan, L.: A surface reconstruction method using global graph cut optimization. Int. J. Comput. Vision 66(2), 141–161 (2006)CrossRefGoogle Scholar
  12. 12.
    Gargallo, P., Prados, E., Sturm, P.: Minimizing the reprojection error in surface reconstruction from images. In: Proceedings of the International Conference on Computer Vision, Rio de Janeiro, Brazil, IEEE Computer Society Press, Los Alamitos (2007)Google Scholar
  13. 13.
    Hernández, C., Vogiatzis, G., Cipolla, R.: Probabilistic visibility for multi-view stereo. In: Computer Vision and Pattern Recognition 2007, Minneapolis (2007)Google Scholar
  14. 14.
    Minka, T.: Divergence measures and message passing. Technical report, Microsoft Research (2005)Google Scholar
  15. 15.
    Wainwright, M., Jaakkola, T., Willsky, A.: Map estimation via agreement on trees: message-passing and linear programming. Information Theory, IEEE Transactions on 51, 3697–3717 (2005)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Pau Gargallo
    • 1
  • Peter Sturm
    • 1
  • Sergi Pujades
    • 1
  1. 1.INRIA Rhône-Alpes and Laboratoire Jean KuntzmannFrance

Personalised recommendations