Total Absolute Gaussian Curvature for Stereo Prior

  • Hiroshi Ishikawa
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4844)


In spite of the great progress in stereo matching algorithms, the prior models they use, i.e., the assumptions about the probability to see each possible surface, have not changed much in three decades. Here, we introduce a novel prior model motivated by psychophysical experiments. It is based on minimizing the total sum of the absolute value of the Gaussian curvature over the disparity surface. Intuitively, it is similar to rolling and bending a flexible paper to fit to the stereo surface, whereas the conventional prior is more akin to spanning a soap film. Through controlled experiments, we show that the new prior outperforms the conventional models, when compared in the equal setting.


Convex Hull Gaussian Curvature Belief Propagation Prior Model Stereo Vision 
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.
    Alboul, L., van Damme, R.: Polyhedral metrics in surface reconstruction: Tight triangulations. In: The Mathematics of Surfaces VII, pp. 309–336. Clarendon Press, Oxford (1997)Google Scholar
  2. 2.
    Belhumeur, P.N.: A Bayesian Approach to Binocular Stereopsis. Int. J. Comput. Vision 19, 237–262 (1996)CrossRefGoogle Scholar
  3. 3.
    Blake, A., Zisserman, A.: Visual reconstruction. MIT Press, Cambridge, MA (1987)Google Scholar
  4. 4.
    Birchfield, S., Tomasi, C.: Multiway cut for stereo and motion with slanted surfaces. In: ICCV 1999, vol. I, pp. 489–495 (1999)Google Scholar
  5. 5.
    Boykov, Y., Veksler, O., Zabih, R.: Fast Approximate Energy Minimization via Graph Cuts. IEEE Trans. on Patt. Anal. Machine Intell. 23, 1222–1239 (2001)CrossRefGoogle Scholar
  6. 6.
    Buchin, M., Giesen, J.: Minimizing the Total Absolute Gaussian Curvature in a Terrain is Hard. In: the 17th Canadian Conference on Computational Geometry, pp. 192–195 (2005)Google Scholar
  7. 7.
    Faugeras, O.: Three-Dimensional Computer Vision. MIT Press, Cambridge, MA (1993)Google Scholar
  8. 8.
    Felzenszwalb, P., Huttenlocher, D.: Efficient Belief Propagation for Early Vision. In: CVPR 2004, pp. 261–268 (2004)Google Scholar
  9. 9.
    Grimson, W.E.: From Images to Surfaces. MIT Press, Cambridge, MA (1981)Google Scholar
  10. 10.
    Ishikawa, H.: Exact Optimization for Markov Random Fields with Convex Priors. IEEE Trans. on Patt. Anal. Machine Intell. 25(10), 1333–1336 (2003)CrossRefGoogle Scholar
  11. 11.
    Ishikawa, H., Geiger, D.: Occlusions, Discontinuities, and Epipolar Lines in Stereo. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 232–248. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  12. 12.
    Ishikawa, H., Geiger, D.: Rethinking the Prior Model for Stereo. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 526–537. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  13. 13.
    Ishikawa, H., Geiger, D.: Illusory Volumes in Human Stereo Perception. Vision Research 46(1-2), 171–178 (2006)CrossRefGoogle Scholar
  14. 14.
    Jones, J., Malik, J.: Computational Framework for Determining Stereo Correspondence from a set of linear spatial filters. Image Vision Comput. 10, 699–708 (1992)CrossRefGoogle Scholar
  15. 15.
    Kanizsa, G.: Organization in Vision. Praeger, New York (1979)Google Scholar
  16. 16.
    Kolmogorov, V., Zabih, R.: Computing Visual Correspondence with Occlusions via Graph Cuts. In: ICCV 2001, pp. 508–515 (2001)Google Scholar
  17. 17.
    Marr, D., Poggio, T.: Cooperative Computation of Stereo Disparity. Science 194, 283–287 (1976)CrossRefGoogle Scholar
  18. 18.
    Meltzer, T., Yanover, C., Weiss, Y.: Globally Optimal Solutions for Energy Minimization in Stereo Vision Using Reweighted Belief Propagation. In: ICCV 2005, pp. 428–435 (2005)Google Scholar
  19. 19.
    Ogale, A.S., Aloimonos, Y.: Stereo correspondence with slanted surfaces: critical implications of horizontal slant. In: CVPR 2004, vol. I, pp. 568–573 (2004)Google 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: ICCV 1998, 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 Publishers, Boston, MA (1989)Google Scholar
  24. 24.
    Sun, J., Zhen, N.N, Shum, H.Y.: Stereo Matching Using Belief Propagation. IEEE Trans. on Patt. Anal. Machine Intell. 25, 787–800 (2003)CrossRefGoogle Scholar
  25. 25.
    Tappen, M.F., Freeman, W.T.: Comparison of Graph Cuts with Belief Propagation for Stereo, using Identical MRF Parameters. In: ICCV 2003, vol. II, pp. 900–907 (2003)Google Scholar
  26. 26.
    Terzopoulos, D.: Regularization of Inverse Visual Problems Involving Discontinuities. IEEE Trans. on Patt. Anal. Machine Intell. 8, 413–424 (1986)CrossRefGoogle Scholar
  27. 27.
    Veksler, O.: Graph Cut Based Optimization for MRFs with Truncated Convex Priors. In: CVPR 2007 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Hiroshi Ishikawa
    • 1
  1. 1.Department of Information and Biological Sciences, Nagoya City University, Nagoya 467-8501Japan

Personalised recommendations