Uncertainty Driven Multi-scale Optimization

  • Pushmeet Kohli
  • Victor Lempitsky
  • Carsten Rother
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6376)


This paper proposes a new multi-scale energy minimization algorithm which can be used to efficiently solve large scale labelling problems in computer vision. The basic modus operandi of any multi-scale method involves the construction of a smaller problem which can be solved efficiently. The solution of this problem is used to obtain a partial labelling of the original energy function, which in turn allows us to minimize it by solving its (much smaller) projection. We propose the use of new techniques for both the construction of the smaller problem, and the extraction of a partial solution. Experiments on image segmentation show that our techniques give solutions with low pixel labelling error and in the same or less amount of computation time, compared to traditional multi-scale techniques.


Partial Solution Laplacian Pyramid Pairwise Potential Partial Labelling Original Energy 
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.
    Boykov, Y., Jolly, M.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: ICCV, pp. I: 105–112 (2001)Google Scholar
  2. 2.
    Boykov, Y., Kolmogorov, V.: Computing geodesics and minimal surfaces via graph cuts. In: ICCV, pp. 26–33 (2003)Google Scholar
  3. 3.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. PAMI (2001)Google Scholar
  4. 4.
    Gidas, B.: A renormalization group approach to image processing problems. PAMI (1989)Google Scholar
  5. 5.
    Glocker, B., Paragios, N., Komodakis, N., Tziritas, G., Navab, N.: Optical flow estimation with uncertainties through dynamic mrfs. In: CVPR (2008)Google Scholar
  6. 6.
    Kohli, P., Torr, P.: Efficiently solving dynamic markov random fields using graph cuts. In: ICCV, vol. II, pp. 922–929 (2005)Google Scholar
  7. 7.
    Kopf, J., Uyttendaele, M., Deussen, O., Cohen, M.F.: Capturing and viewing gigapixel images. ACM Trans. Graph. (2007)Google Scholar
  8. 8.
    Lempitsky, V.S., Boykov, Y.: Global optimization for shape fitting. In: CVPR (2007)Google Scholar
  9. 9.
    Lombaert, H., Sun, Y., Grady, L., Xu, C.: A multilevel banded graph cuts method for fast image segmentation. In: ICCV (2005)Google Scholar
  10. 10.
    Pérez, P., Heitz, F.: Restriction of a markov random field on a graph and multiresolution statistical image modeling. IEEE Trans. on Inf. Theory (1996)Google Scholar
  11. 11.
    Puzicha, J., Buhmann, J.: Multiscale annealing for grouping and unsupervised texture segmentation. In: CVIU (1999)Google Scholar
  12. 12.
    Rother, C., Kolmogorov, V., Blake, A.: Grabcut: interactive foreground extraction using iterated graph cuts. In: SIGGRAPH, pp. 309–314 (2004)Google Scholar
  13. 13.
    Sinop, A.K., Grady, L.: Accurate banded graph cut segmentation of thin structures using laplacian pyramids. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4191, pp. 896–903. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Pushmeet Kohli
    • 1
  • Victor Lempitsky
    • 2
  • Carsten Rother
    • 1
  1. 1.Microsoft Research Cambridge 
  2. 2.University of Oxford 

Personalised recommendations