Abstract
Belief propagation (BP) has become widely used for low-level vision problems and various inference techniques have been proposed for loopy graphs. These methods typically rely on ad hoc spatial priors such as the Potts model. In this paper we investigate the use of learned models of image structure, and demonstrate the improvements obtained over previous ad hoc models for the image denoising problem. In particular, we show how both pairwise and higher-order Markov random fields with learned clique potentials capture rich image structures that better represent the properties of natural images. These models are learned using the recently proposed Fields-of-Experts framework. For such models, however, traditional BP is computationally expensive. Consequently we propose some approximation methods that make BP with learned potentials practical. In the case of pairwise models we propose a novel approximation of robust potentials using a finite family of quadratics. In the case of higher order MRFs, with 2× 2 cliques, we use an adaptive state space to handle the increased complexity. Extensive experiments demonstrate the power of learned models, the benefits of higher-order MRFs and the practicality of BP for these problems with the use of simple principled approximations.
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
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE PAMI 23(11), 1222–1239 (2001)
Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE PAMI 26(9), 1124–1137 (2004)
Kolmogorov, V., Zabih, R.: Multi-camera scene reconstruction via graph cuts. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 82–96. Springer, Heidelberg (2002)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. In: CVPR, vol. 1, pp. 261–268 (2004)
Tappen, M.F., Russell, B.C., Freeman, W.T.: Efficient graphical models for processing images. In: CVPR, vol. 2, pp. 673–680 (2004)
Yedidia, J.S., Freeman, W.T., Weiss, Y.: Constructing free energy approximations and generalized belief propagation algorithms. Technical Report TR-2004-040, Mitsubishi Electric Research Laboratories, Cambridge, Massachusetts (2004)
Zhu, S.C., Wu, Y., Mumford, D.: Filters, random fields and maximum entropy (FRAME): Towards a unified theory for texture modeling. IJCV 27(2), 107–126 (1998)
Paget, R., Longstaff, I.D.: Texture synthesis via a noncausal nonparametric multiscale Markov random field. IEEE T. Image Proc. 7(6), 925–931 (1998)
Roth, S., Black, M.J.: Fields of experts: A framework for learning image priors. In: CVPR, vol. 2, pp. 860–867 (2005)
Geman, S., Geman, D.: Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images. IEEE PAMI 6, 721–741 (1984)
Gimel’farb, G.L.: Texture modeling by multiple pairwise pixel interactions. IEEE PAMI 18(11), 1110–1114 (1996)
Zalesny, A., van Gool, L.: A compact model for viewpoint dependent texture synthesis. In: Pollefeys, M., Van Gool, L., Zisserman, A., Fitzgibbon, A.W. (eds.) SMILE 2000. LNCS, vol. 2018, pp. 124–143. Springer, Heidelberg (2001)
Huang, J.: Statistics of Natural Images and Models. PhD thesis, Brown University (2000)
Hinton, G.E.: Products of experts. In: ICANN, vol. 1, pp. 1–6 (1999)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV, vol. 2, pp. 416–423 (2001)
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neur. Comp. 14(8), 1771–1800 (2002)
Agarwala, A., Dontcheva, M., Agrawala, M., Drucker, S., Colburn, A., Curless, B., Salesin, D.H., Cohen, M.: Interactive digital photomontage. ACM SIGGRAPH 23(3), 294–302 (2004)
Tappen, M.F., Freeman, W.T.: Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters. In: ICCV, vol. 2, pp. 900–907 (2003)
Kschischang, F.R., Frey, B.J., Loelinger, H.A.: Fractor graphs and the sum-product algorithm. IEEE T. Info. Th. 47(2), 498–519 (2001)
Sun, J., Zhen, N.N., Shum, H.Y.: Stereo matching using belief propagation. IEEE PAMI 25(7), 787–800 (2003)
Black, M.J., Rangarajan, A.: On the unification of line processes, outlier rejection, and robust statistics with applications in early vision. IJCV 19(1), 57–92 (1996)
Portilla, J., Strela, V., Wainwright, M.J., Simoncelli, E.P.: Image denoising using scale mixtures of Gaussians in the wavelet domain. IEEE T. Image Proc. 12(11), 1338–1351 (2003)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: From error visibility to structural similarity. IEEE T. Image Proc. 13(4), 600–612 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lan, X., Roth, S., Huttenlocher, D., Black, M.J. (2006). Efficient Belief Propagation with Learned Higher-Order Markov Random Fields. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3952. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744047_21
Download citation
DOI: https://doi.org/10.1007/11744047_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33834-5
Online ISBN: 978-3-540-33835-2
eBook Packages: Computer ScienceComputer Science (R0)