International Journal of Computer Vision

, Volume 70, Issue 1, pp 41–54 | Cite as

Efficient Belief Propagation for Early Vision

Article

Abstract

Markov random field models provide a robust and unified framework for early vision problems such as stereo and image restoration. Inference algorithms based on graph cuts and belief propagation have been found to yield accurate results, but despite recent advances are often too slow for practical use. In this paper we present some algorithmic techniques that substantially improve the running time of the loopy belief propagation approach. One of the techniques reduces the complexity of the inference algorithm to be linear rather than quadratic in the number of possible labels for each pixel, which is important for problems such as image restoration that have a large label set. Another technique speeds up and reduces the memory requirements of belief propagation on grid graphs. A third technique is a multi-grid method that makes it possible to obtain good results with a small fixed number of message passing iterations, independent of the size of the input images. Taken together these techniques speed up the standard algorithm by several orders of magnitude. In practice we obtain results that are as accurate as those of other global methods (e.g., using the Middlebury stereo benchmark) while being nearly as fast as purely local methods.

Keywords

belief propagation Markov random fields stereo image restoration efficient algorithms 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Birchfield, S. and Tomasi, C. 1998. A pixel dissimilarity measure that is insensitive to image sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(4):401–406.CrossRefGoogle Scholar
  2. Blake, A. and Zisserman, A. 1987. Visual Reconstruction. MIT Press.Google Scholar
  3. Borgefors G. 1986. Distance transformations in digital images. Computer Vision, Graphics and Image Processing, 34(3):344–371.Google Scholar
  4. Boykov, Y., Veksler, O., and Zabih, R. 2001. Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(11):1222–1239.CrossRefGoogle Scholar
  5. Burt, P.J. and Adelson, E.H. 1983. The laplacian pyramid as a compact image code. IEEE Transactions on Communication, 31(4):532–540.CrossRefGoogle Scholar
  6. Devillers, O. and Golin, M. 1995. Incremental algorithms for finding the convex hulls of circles and the lower envelopes of parabolas. Inform. Process. Lett., 56(3):157–164.MathSciNetCrossRefMATHGoogle Scholar
  7. Felzenszwalb, P.F. and Huttenlocher, D.P. 2004. Distance transforms of sampled functions. Cornell Computing and Information Science Technical Report TR2004-1963.Google Scholar
  8. Geman, S. and Geman, D. 1984. Stochastic relaxation, gibbs distributions, and the bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6(6):721–741.CrossRefMATHGoogle Scholar
  9. Scharstein, D. and Szeliski, R. 2002. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47(1):7–42.Google Scholar
  10. Sun, J., Zheng, N.N., and Shum, H.Y. 2003. Stereo matching using belief propagation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(7):787–800.CrossRefGoogle Scholar
  11. Tappen, M.F. and Freeman, W.T. 2003. Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters. In IEEE International Conference on Computer Vision.Google Scholar
  12. Weiss, Y. and Freeman, W.T. 2001. On the optimality of solutions of the max-product belief propagation algorithm in arbitrary graphs. IEEE Transactions on Information Theory, 47(2):723–735.MathSciNetCrossRefGoogle Scholar
  13. Wells, W.M. 1986. Efficient systhesis of gaussian filters by cascaded uniform filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(2):234–239.Google Scholar
  14. Willsky, A.S. 2002. Multiresolution markov models for signal and image processing. Proceedings of the IEEE, 90(8):1396–1458.Google Scholar

Copyright information

© Springer Science + Business Media, LLC 2006

Authors and Affiliations

  • Pedro F. Felzenszwalb
    • 1
  • Daniel P. Huttenlocher
    • 2
  1. 1.Computer Science DepartmentUniversity of ChicagoChicago
  2. 2.Computer Science DepartmentCornell UniversityUSA

Personalised recommendations