Abstract
We describe a new fast algorithm for multi-labelling problems. In general, a multi-labelling problem is NP-hard. Widely used algorithms like α-expansion can reach a suboptimal result in a time linear in the number of the labels. In this paper, we propose an algorithm which can obtain results of comparable quality polynomially faster. We use the Divide and Conquer paradigm to separate the complexities induced by the label set and the variable set, and deal with each of them respectively. Such a mechanism improves the solution speed without depleting the memory resource, hence it is particularly valuable for applications where the variable set and the label set are both huge. Another merit of the proposed method is that the trade-off between quality and time efficiency can be varied through using different parameters. The advantage of our method is validated by experiments.
Chapter PDF
Similar content being viewed by others
Keywords
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.
References
Zabih, R., Veksler, O., Boykov, Y.: Fast approximate energy minimization via graph cuts. In: ICCV 1999, pp. 377–384 (1999)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 1222–1239 (2001)
Komodakis, N., Tziritas, G., Paragios, N.: Performance vs computational efficiency for optimizing single and dynamic mrfs: Setting the state of the art with primal-dual strategies. Comput. Vis. Image Underst. 112, 14–29 (2008)
Komodakis, N., Tziritas, G.: Approximate labeling via graph cuts based on linear programming. PAMI 29, 1436–1453 (2007)
Boros, E., Hammer, P.L.: Pseudo-boolean optimization. Discrete Applied Mathematics 123, 155–225 (2002)
Carr, P., Hartley, R.: Solving multilabel graph cut problems using multilabel swap. In: DICTA, Melbourne, Australia (2009)
Carr, P., Hartley, R.: Minimizing energy functions on 4-connected lattices using elimination. In: ICCV, Kyoto, Japan (2009)
Kohli, P., Torr, P.: Dynamic graph cuts for efficient inference in markov random fields. PAMI 29, 2079–2088 (2007)
Goldberg, A.V., Rao, S.: Beyond the flow decomposition barrier. J. ACM 45, 783–797 (1998)
Rother, C., Kolmogorov, V., Lempitsky, V., Szummer, M.: Optimizing binary mrfs via extended roof duality. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2007)
Gould, S., Amat, F., Koller, D.: Alphabet SOUP: A framework for approximate energy minimization. In: CVPR (2009)
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, 1068–1080 (2008)
Scharstein, D., Szeliski, R., Zabih, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. SMBV 2001: Proceedings of the IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001), p. 131 (2001)
Wang, L., Jin, H., Yang, R.: Search space reduction for mrf stereo. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 576–588. Springer, Heidelberg (2008)
Veksler, O.: Reducing search space for stereo correspondence with graph cuts. In: BMVC 2006, vol. II, p. 709 (2006)
Hirschmuller, H., Scharstein, D.: Evaluation of cost functions for stereo matching. In: CVPR 2007 (2007)
Scharstein, D., Pal, C.: Learning conditional random fields for stereo. In: CVPR 2007 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, Y., Hartley, R., Wang, L. (2010). Fast Multi-labelling for Stereo Matching. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6313. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15558-1_38
Download citation
DOI: https://doi.org/10.1007/978-3-642-15558-1_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15557-4
Online ISBN: 978-3-642-15558-1
eBook Packages: Computer ScienceComputer Science (R0)