Convex Relaxation for Multilabel Problems with Product Label Spaces

  • Bastian Goldluecke
  • Daniel Cremers
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6315)


Convex relaxations for continuous multilabel problems have attracted a lot of interest recently [1,2,3,4,5]. Unfortunately, in previous methods, the runtime and memory requirements scale linearly in the total number of labels, making them very inefficient and often unapplicable for problems with higher dimensional label spaces. In this paper, we propose a reduction technique for the case that the label space is a product space, and introduce proper regularizers. The resulting convex relaxation requires orders of magnitude less memory and computation time than previously, which enables us to apply it to large-scale problems like optic flow, stereo with occlusion detection, and segmentation into a very large number of regions. Despite the drastic gain in performance, we do not arrive at less accurate solutions than the original relaxation. Using the novel method, we can for the first time efficiently compute solutions to the optic flow functional which are within provable bounds of typically 5% of the global optimum.


Convex Relaxation Convex Envelope Label Space Occlusion Detection Occlude Pixel 
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.
    Lellmann, J., Becker, F., Schnörr, C.: Convex optimization for multi-class image labeling with a novel family of total variation based regularizers. In: IEEE International Conference on Computer Vision (ICCV) (2009)Google Scholar
  2. 2.
    Nikolova, M., Esedoglu, S., Chan, T.: Algorithms for finding global minimizers of image segmentation and denoising models. SIAM Journal of Applied Mathematics 66, 1632–1648 (2006)zbMATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Pock, T., Schoenemann, T., Graber, G., Bischof, H., Cremers, D.: A convex formulation of continuous multi-label problems. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 792–805. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  4. 4.
    Pock, T., Chambolle, A., Bischof, H., Cremers, D.: A convex relaxation approach for computing minimal partitions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 810–817 (2009)Google Scholar
  5. 5.
    Zach, C., Gallup, D., Frahm, J., Niethammer, M.: Fast global labeling for real-time stereo using multiple plane sweeps. In: Vision, Modeling and Visualization, pp. 243–252 (2009)Google Scholar
  6. 6.
    Szeliski, R.: Bayesian modeling of uncertainty in low-level vision. International Journal of Computer Vision 5, 271–301 (1990)CrossRefGoogle Scholar
  7. 7.
    Kindermann, R., Snell, J.: Markov Random Fields and Their Applications. American Mathematical Society, Providence (1980)Google Scholar
  8. 8.
    Boykov, Y., Kolmogorov, V.: Computing geodesics and minimal surfaces via graph cuts. In: IEEE International Conference on Computer Vision (ICCV), pp. 26–33 (2003)Google Scholar
  9. 9.
    Greig, D., Porteous, B., Seheult, A.: Exact maximum a posteriori estimation for binary images. J. Royal Statistics Soc. 51, 271–279 (1989)Google Scholar
  10. 10.
    Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 26, 147–159 (2004)CrossRefGoogle Scholar
  11. 11.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 1222–1239 (2001)CrossRefGoogle Scholar
  12. 12.
    Schlesinger, D., Flach, B.: Transforming an arbitrary min-sum problem into a binary one. Technical report, Dresden University of Technology (2006)Google Scholar
  13. 13.
    Wainwright, M., Jaakkola, T., Willsky, A.: Map estimation via agreement on trees: message-passing and linear programming. IEEE Trans. Inf. Theory 51, 3697–3717 (2005)CrossRefMathSciNetGoogle Scholar
  14. 14.
    Ishikawa, H.: Exact optimization for markov random fields with convex priors. IEEE Trans. Pattern Anal. Mach. Intell. 25, 1333–1336 (2003)CrossRefGoogle Scholar
  15. 15.
    Klodt, M., Schoenemann, T., Kolev, K., Schikora, M., Cremers, D.: An experimental comparison of discrete and continuous shape optimization methods. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 332–345. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  16. 16.
    Popov, L.: A modification of the arrow-hurwicz method for search of saddle points. Math. Notes 28, 845–848 (1980)Google Scholar
  17. 17.
    Nesterov, Y.: Smooth minimization of non-smooth functions. Math. Prog. 103, 127–152 (2004)CrossRefMathSciNetGoogle Scholar
  18. 18.
    Beck, A., Teboulle, M.: Fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sciences 2, 183–202 (2009)zbMATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV − L 1 optical flow. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  20. 20.
    Duval, V., Aujol, J.F., Vese, L.: Projected gradient based color image decomposition. In: Tai, X.-C., Mørken, K., Lysaker, M., Lie, K.-A. (eds.) Scale Space and Variational Methods in Computer Vision. LNCS, vol. 5567, pp. 295–306. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  21. 21.
    Michelot, C.: A finite algorithm for finding the projection of a point onto the canonical simplex of \(\mathbb R{n}\). J. Optimization Theory and Applications 50, 195–200 (1986)zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Bastian Goldluecke
    • 1
  • Daniel Cremers
    • 1
  1. 1.Computer Vision GroupTU Munich 

Personalised recommendations