Continuous Energy Minimization Via Repeated Binary Fusion

  • Werner Trobin
  • Thomas Pock
  • Daniel Cremers
  • Horst Bischof
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5305)


Variational problems, which are commonly used to solve low-level vision tasks, are typically minimized via a local, iterative optimization strategy, e.g. gradient descent. Since every iteration is restricted to a small, local improvement, the overall convergence can be slow and the algorithm may get stuck in an undesirable local minimum. In this paper, we propose to approximate the minimization by solving a series of binary subproblems to facilitate large optimization moves. The proposed method can be interpreted as an extension of discrete graph-cut based methods such as α-expansion or LogCut to a spatially continuous setting. In order to demonstrate the viability of the approach, we evaluated the novel optimization strategy in the context of optical flow estimation, yielding excellent results on the Middlebury optical flow datasets.


Markov Random Field Optical Flow Estimation Average Angular Error Propose Optimization Strategy Ground Truth Disparity 
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.
    Mumford, D.: Bayesian rationale for energy functionals. In: Geometry-driven diffusion in Computer Vision, pp. 141–153. Kluwer Academic Publishers, Dordrecht (1994)Google Scholar
  2. 2.
    Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., Tappen, M., Rother, C.: A comparative study of energy minimization methods for Markov random fields with smoothness-based priors. IEEE Trans. Pattern Anal. Mach. Intell. 30(6), 1068–1080 (2008)CrossRefGoogle Scholar
  3. 3.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1988)Google Scholar
  4. 4.
    Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. IEEE Trans. Pattern Anal. Mach. Intell. 28(10), 1568–1583 (2006)CrossRefGoogle Scholar
  5. 5.
    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
  6. 6.
    Veksler, O.: Graph cut based optimization for MRFs with truncated convex priors. In: Proc. of the CVPR (June 2007)Google Scholar
  7. 7.
    Lempitsky, V., Rother, C., Blake, A.: LogCut – efficient graph cut optimization for Markov random fields. In: Proc. of the ICCV (October 2007)Google Scholar
  8. 8.
    Komodakis, N., Tziritas, G., Paragios, N.: Fast, approximately optimal solutions for single and dynamic MRFs. In: Proc. of the CVPR (June 2007)Google Scholar
  9. 9.
    Chambolle, A.: Total variation minimization and a class of binary MRF models. Energy Minimization Methods in Comp. Vision and Pattern Rec. 136–152 (2005)Google Scholar
  10. 10.
    Nikolova, M., Esedoglu, S., Chan, T.F.: Algorithms for finding global minimizers of image segmentation and denoising models. SIAM J. on App. Math. 66 (2006)Google Scholar
  11. 11.
    Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)CrossRefGoogle Scholar
  12. 12.
    Black, M.J., Anandan, P.: A framework for the robust estimation of optical flow. In: Proc. of the ICCV, pp. 231–236 (May 1993)Google Scholar
  13. 13.
    Aubert, G., Deriche, R., Kornprobst, P.: Computing optical flow via variational techniques. SIAM Journal on Applied Mathematics 60(1), 156–182 (2000)CrossRefMathSciNetGoogle Scholar
  14. 14.
    Papenberg, N., Bruhn, A., Brox, T., Didas, S., Weickert, J.: Highly accurate optic flow computation with theoretically justified warping. International Journal of Computer Vision 67(2), 141–158 (2006)CrossRefGoogle Scholar
  15. 15.
    Bruhn, A., Weickert, J., Kohlberger, T., Schnörr, C.: A multigrid platform for real-time motion computation with discontinuity-preserving variational methods. International Journal of Computer Vision 70(3), 257–277 (2006)CrossRefGoogle Scholar
  16. 16.
    Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L1 optical flow. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  17. 17.
    Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M., Szeliski, R.: A database and evaluation methodology for optical flow. In: Proc. of the ICCV (2007)Google Scholar
  18. 18.
    Aujol, J.F., Gilboa, G., Chan, T.F., Osher, S.: Structure-texture image decomposition – modeling, algorithms, and parameter selection. International Journal of Computer Vision 67(1), 111–136 (2006)CrossRefGoogle Scholar
  19. 19.
    Rudin, L., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D 60, 259–268 (1992)zbMATHCrossRefGoogle Scholar
  20. 20.
    Chambolle, A.: An algorithm for total variation minimization and applications. Journal of Mathematical Imaging and Vision 20, 89–97 (2004)CrossRefMathSciNetGoogle Scholar
  21. 21.
    Trobin, W., Pock, T., Cremers, D., Bischof, H.: An unbiased second-order prior for high-accuracy motion estimation. In: Rigoll, G. (ed.) DAGM 2008. LNCS, vol. 5096, pp. 396–405. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  22. 22.
    Danielsson, P.E., Lin, Q.: Efficient detection of second-degree variations in 2D and 3D images. Journal of Visual Comm. and Image Representation 12, 255–305 (2001)CrossRefGoogle Scholar
  23. 23.
    Kohli, P., Kumar, P., Torr, P.H.: P3 & beyond: Solving energies with higher order cliques. In: Proc. of the CVPR (June 2007)Google Scholar
  24. 24.
    Pock, T., Schoenemann, T., Cremers, D., Bischof, H.: A convex formulation of continuous multi-label problems. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5304, pp. 792–805. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  25. 25.
    Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. In: Proc. of the CVPR, vol. 1, pp. 195–202 (June 2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Werner Trobin
    • 1
  • Thomas Pock
    • 1
    • 2
  • Daniel Cremers
    • 2
  • Horst Bischof
    • 1
  1. 1.Institute for Computer Graphics and VisionGraz University of Technology 
  2. 2.Department of Computer ScienceUniversity of Bonn 

Personalised recommendations