Rethinking the Prior Model for Stereo

  • Hiroshi Ishikawa
  • Davi Geiger
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3953)


Sometimes called the smoothing assumption, the prior model of a stereo matching algorithm is the algorithm’s expectation on the surfaces in the world. Any stereo algorithm makes assumptions about the probability to see each surface that can be represented in its representation system. Although the past decade has seen much continued progress in stereo matching algorithms, the prior models used in them have not changed much in three decades: most algorithms still use a smoothing prior that minimizes some function of the difference of depths between neighboring sites, sometimes allowing for discontinuities.

However, one system seems to use a very different prior model from all other systems: the human vision system. In this paper, we first report the observations we made in examining human disparity interpolation using stereo pairs with sparse identifiable features. Then we mathematically analyze the implication of using current prior models and explain why the human system seems to use a model that is not only different but in a sense diametrically opposite from all current models. Finally, we propose two candidate models that reflect the behavior of human vision. Although the two models look very different, we show that they are closely related.


Convex Hull Human Vision System Human Vision Prior Model Stereo Pair 
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.
    Ayache, N.: Artificial Vision for Mobile Robots. MIT Press, Cambridge (1991)Google Scholar
  2. 2.
    Belhumeur, P.N.: A Bayesian approach to binocular stereopsis. J. Comput. Vision 19, 237–262 (1996)CrossRefGoogle Scholar
  3. 3.
    Belhumeur, P.N., Mumford, D.: A Bayesian treatment of the stereo correspondence problem using half-occluded regions. In: Proc. CVPR 1992, pp. 506–512 (1992)Google Scholar
  4. 4.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE T. PAMI 23, 1222–1239 (2001)Google Scholar
  5. 5.
    Faugeras, O.: Three-Dimensional Computer Vision. MIT Press, Cambridge (1993)Google Scholar
  6. 6.
    Geiger, D., Ladendorf, B., Yuille, A.: Occlusions and binocular stereo. Int. J. Comput. Vision 14, 211–226 (1995)CrossRefGoogle Scholar
  7. 7.
    Gillam, B., Borsting, E.: The role of monocular regions in stereoscopic displays. Perception 17, 603–608 (1988)CrossRefGoogle Scholar
  8. 8.
    Grimson, W.E.: From Images to Surfaces. MIT Press, Cambridge (1981)Google Scholar
  9. 9.
    Ishikawa, H., Geiger, D.: Occlusions, discontinuities, and epipolar lines in stereo. In: Fifth European Conference on Computer Vision, Freiburg, Germany, pp. 232–248 (1998)Google Scholar
  10. 10.
    Jones, J., Malik, J.: Image Vision Comput. 10, 699–708 (1992)Google Scholar
  11. 11.
    Kanizsa, G.: Organization in Vision. Praeger, New York (1979)Google Scholar
  12. 12.
    Kolmogorov, V., Zabih, R.: Computing Visual Correspondence with Occlusions via Graph Cuts. In: ICCV 2001, Vancouver, Canada, pp. 508–515 (2001)Google Scholar
  13. 13.
    Malik, J.: On Binocularly viewed occlusion Junctions. In: Fourth European Conference on Computer Vision, vol. 1, pp. 167–174 (1996)Google Scholar
  14. 14.
    Mamassian, P., Landy, M.S.: Observer biases in the 3D interpretation of line drawings. Vision Research 38, 2817–2832 (1998)CrossRefGoogle Scholar
  15. 15.
    Marr, D., Poggio, T.: Cooperative computation of stereo disparity. Science 194, 283–287 (1976)CrossRefGoogle Scholar
  16. 16.
    Marr, D., Poggio, T.: A computational theory of human stereo vision. Proc. R. Soc. Lond. B 204, 301–328 (1979)CrossRefGoogle Scholar
  17. 17.
    Nakayama, K., Shimojo, S.: Da Vinci stereopsis: depth and subjective occluding contours from unpaired image points. Vision Research 30, 1811–1825 (1990)CrossRefGoogle Scholar
  18. 18.
    Pollard, S.B., Mayhew, J.E.W., Frisby, J.P.: PMF: A stereo correspondence algorithm using a disparity gradient. Perception 14, 449–470 (1985)CrossRefGoogle Scholar
  19. 19.
    Poggio, G., Poggio, T.: The Analysis of Stereopsis. Annu. Rev. Neurosci. 7, 379–412 (1984)CrossRefGoogle Scholar
  20. 20.
    Roy, S.: Stereo without epipolar lines: A maximum-flow formulation. Int. J. Comput. Vision 34, 147–162 (1999)CrossRefGoogle Scholar
  21. 21.
    Roy, S., Cox, I.: A maximum-flow formulation of the N-camera stereo correspondence problem. In: International Conference on Computer Vision, Bombai, India, pp. 492–499 (1998)Google Scholar
  22. 22.
    Scharstein, D., Szeliski, R.: A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. Int. J. Computer Vision 47, 7–42 (2002)zbMATHCrossRefGoogle Scholar
  23. 23.
    Szeliski, R.: A Bayesian modelling of uncertainty in low-level vision. Kluwer Academic Press, Boston (1989)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hiroshi Ishikawa
    • 1
  • Davi Geiger
    • 2
  1. 1.Department of Information and Biological SciencesNagoya City UniversityNagoyaJapan
  2. 2.Courant Institute of Mathematical SciencesNew York UniversityNew YorkUSA

Personalised recommendations