Differential Geometric Consistency Extends Stereo to Curved Surfaces

  • Gang Li
  • Steven W. Zucker
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3953)


Traditional stereo algorithms implicitly use the frontal parallel plane assumption when exploiting contextual information, since the smoothness prior biases towards constant disparity (depth) over a neighborhood. For curved surfaces these algorithms introduce systematic errors to the matching process. These errors are non-negligible for detailed geometric modeling of natural objects (e.g. a human face). We propose to use contextual information geometrically. In particular, we perform a differential geometric study of smooth surfaces and argue that geometric contextual information should be encoded in Cartan’s moving frame model over local quadratic approximations of the smooth surfaces. The result enforces geometric consistency for both depth and surface normal. We develop a simple stereo algorithm to illustrate the importance of using such geometric contextual information and demonstrate its power on images of the human face.


Tangent Plane Shape Operator Stereo Pair Candidate Match Stereo Correspondence 
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.
    Belhumeur, P.N.: A bayesian approach to binocular stereopsis. IJCV 19(3), 237–262 (1996)CrossRefGoogle Scholar
  2. 2.
    Birchfield, S., Tomasi, C.: Multiway cut for stereo and motion with slanted surfaces. In: Proc. ICCV (1999)Google Scholar
  3. 3.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. on PAMI 23(11), 1222–1239 (2001)Google Scholar
  4. 4.
    Cipolla, R., Giblin, P.: Visual Motion of Curves and Surfaces. Cambridge University Press, Cambridge (2000)zbMATHGoogle Scholar
  5. 5.
    Devernay, F., Faugeras, O.D.: Computing differential properties of 3-d shapes from stereoscopic images without 3-d models. In: Proc. CVPR (1994)Google Scholar
  6. 6.
    do Carmo, M.P.: Differential Geometry of Curves and Surfaces. Prentice-Hall, Englewood Cliffs (1976)zbMATHGoogle Scholar
  7. 7.
    Faugeras, O.: Three-Dimensional Computer Vision. The MIT Press, Cambridge (1993)Google Scholar
  8. 8.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)zbMATHGoogle Scholar
  9. 9.
    Hoff, W., Ahuja, N.: Surfaces from stereo: Integrating feature matching, disparity estimation, and contour detection. IEEE Trans. on PAMI 11(2), 121–136 (1989)Google Scholar
  10. 10.
    Kanade, T., Okutomi, M.: A stereo maching algorithm with an adaptive window: Theory and experiment. IEEE Trans. on PAMI 16(9), 920–932 (1994)Google Scholar
  11. 11.
    Koenderink, J.J.: Solid Shape. MIT Press, Cambridge (1990)Google Scholar
  12. 12.
    Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: Proc. ICCV (2001)Google Scholar
  13. 13.
    Li, G., Zucker, S.W.: A differential geometrical model for contour-based stereo correspondence. In: Proc. IEEE Workshop on Variational, Geometric, and Level Set Methods in Computer Vision, at ICCV 2003 (2003)Google Scholar
  14. 14.
    Li, G., Zucker, S.W.: Stereo for slanted surfaces: First order disparities and normal consistency. In: Rangarajan, A., Vemuri, B.C., Yuille, A.L. (eds.) EMMCVPR 2005. LNCS, vol. 3757, pp. 617–632. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  15. 15.
    Li, G., Zucker, S.W.: Contextual inference in contour-based stereo correspondence. IJCV (2006) (in press)Google Scholar
  16. 16.
    Lin, M.H., Tomasi, C.: Surfaces with occlusions from layered stereo. IEEE Trans. on PAMI 26(8), 1073–1078 (2004)Google Scholar
  17. 17.
    Marr, D., Poggio, T.: Cooperative computation of stereo disparity. Science 194, 283–287 (1976)CrossRefGoogle Scholar
  18. 18.
    O’Neill, B.: Elementary Differential Geometry, 2nd edn. Academic Press, London (1997)zbMATHGoogle Scholar
  19. 19.
    Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Reciples in C, 2nd edn. Cambridge University Press, Cambridge (1992)Google Scholar
  20. 20.
    Sander, P.T., Zucker, S.W.: Inferring surface trace and differential structure from 3-d images. IEEE Trans. on PAMI 12(9), 833–854 (1990)Google Scholar
  21. 21.
    Scharstein, D., Szeliski, R.: Stereo matching with nonlinear diffusion. IJCV 28(2), 155–174 (1998)CrossRefGoogle Scholar
  22. 22.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV 47(1/2/3), 7–42 (2002)zbMATHCrossRefGoogle Scholar
  23. 23.
    Strecha, C., Tuytelaars, T., Gool, L.V.: Dense matching of multiple widebaseline views. In: Proc. ICCV (2003)Google Scholar
  24. 24.
    Sun, J., Zheng, N.-N., Shum, H.-Y.: Stereo matching using belief propagation. IEEE Trans. on PAMI 25(7), 787–800 (2003)Google Scholar
  25. 25.
    Tao, H., Sawhney, H.S., Kumar, R.: A global matching framework for stereo computation. In: Proc. ICCV (2001)Google Scholar
  26. 26.
    Tappen, M.F., Freeman, W.T.: Comparison of graph cuts with belief propagation for stereo, using identical mrf parameters. In: Proc. ICCV (2003)Google Scholar
  27. 27.
    Zitnick, C., Kanade, T.: A cooperative algorithm for stereo mathching and occlusion detection. IEEE Trans. on PAMI 22(7), 675–684 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Gang Li
    • 1
  • Steven W. Zucker
    • 1
  1. 1.Department of Computer ScienceYale UniversityNew HavenUSA

Personalised recommendations