Abstract
Markov random fields (MRFs) have found widespread use as models of natural image and scene statistics. Despite progress in modeling image properties beyond gradient statistics with high-order cliques, and learning image models from example data, existing MRFs only exhibit a limited ability of actually capturing natural image statistics. In this paper we investigate this limitation of previous filter-based MRF models, which appears in contradiction to their maximum entropy interpretation. We argue that this is due to inadequacies in the leaning procedure and suggest various modifications to address them. We demonstrate that the proposed learning scheme allows training more suitable potential functions, whose shape approaches that of a Dirac-delta function, as well as models with larger and more filters. Our experiments not only indicate a substantial improvement of the models’ ability to capture relevant statistical properties of natural images, but also demonstrate a significant performance increase in a denoising application to levels previously unattained by generative approaches.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
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
Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE T. Image Process. 16(8), 2080–2095 (2007)
Geman, D., Reynolds, G.: Constrained restoration and the recovery of discontinuities. IEEE T. Pattern Anal. Mach. Intell. 14(3), 367–383 (1992)
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771–1800 (2002)
Huang, J.: Statistics of Natural Images and Models. Ph.D. thesis, Brown University (2000)
Köster, U., Lindgren, J.T., Hyvärinen, A.: Estimating Markov Random Field Potentials for Natural Images. In: Adali, T., Jutten, C., Romano, J.M.T., Barros, A.K. (eds.) ICA 2009. LNCS, vol. 5441, pp. 515–522. Springer, Heidelberg (2009)
Levin, A., Nadler, B.: Natural image denoising: Optimality and inherent bounds. In: CVPR 2011 (2011)
Lyu, S., Simoncelli, E.P.: Modeling multiscale subbands of photographic images with fields of Gaussian scale mixtures. IEEE T. Pattern Anal. Mach. Intell. 31(4), 693–706 (2009)
Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.: Non-local sparse models for image restoration. In: ICCV 2009 (2009)
McAuley, J.J., Caetano, T., Smola, A.J., Franz, M.O.: Learning high-order MRF priors of color images. In: ICML 2006, pp. 617–624 (2006)
Norouzi, M., Ranjbar, M., Mori, G.: Stacks of convolutional restricted Boltzmann machines for shift-invariant feature learning. In: CVPR 2009 (2009)
Portilla, J., Strela, V., Wainwright, M.J., Simoncelli, E.P.: Image denoising using scale mixtures of Gaussians in the wavelet domain. IEEE T. Image Process. 12(11), 1338–1351 (2003)
Ranzato, M., Mnih, V., Hinton, G.E.: Generating more realistic images using gated MRF’s. In: NIPS 2010 (2010)
Roth, S., Black, M.J.: On the spatial statistics of optical flow. Int. J. Comput. Vision 74(1), 33–50 (2007)
Roth, S., Black, M.J.: Fields of experts. Int. J. Comput. Vision 82(2), 205–229 (2009)
Ruderman, D.L.: The statistics of natural images. Network: Comp. Neural 5(4), 517–548 (1994)
Schmidt, U., Gao, Q., Roth, S.: A generative perspective on MRFs in low-level vision. In: CVPR 2010 (2010)
Tieleman, T.: Training restricted boltzmann machines using approximations to the likelihood gradient. In: ICML 2008 (2008)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: From error visibility to structural similarity. IEEE T. Image Process. 13(4), 600–612 (2004)
Weiss, Y., Freeman, W.T.: What makes a good model of natural images? In: CVPR 2007 (2007)
Welling, M., Hinton, G.E., Osindero, S.: Learning sparse topographic representations with products of Student-t distributions. In: NIPS 2002, pp. 1359–1366 (2002)
Zhu, S.C., Mumford, D.: Prior learning and Gibbs reaction-diffusion. IEEE T. Pattern Anal. Mach. Intell. 19(11), 1236–1250 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gao, Q., Roth, S. (2012). How Well Do Filter-Based MRFs Model Natural Images?. In: Pinz, A., Pock, T., Bischof, H., Leberl, F. (eds) Pattern Recognition. DAGM/OAGM 2012. Lecture Notes in Computer Science, vol 7476. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32717-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-32717-9_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32716-2
Online ISBN: 978-3-642-32717-9
eBook Packages: Computer ScienceComputer Science (R0)