Abstract
Newly emerged probabilistic image patch priors, such as Expected Patch Log-Likelihood (EPLL), have shown excellent performance on image restoration tasks, especially deconvolution, due to its rich expressiveness. However, its applicability is limited by the heavy computation involved in the associated optimization process. Inspired by the recent advances on using regression trees to index priors defined on a Conditional Random Field, we propose a novel discriminative indexing approach on patch-based priors to expedite the optimization process. Specifically, we propose an efficient tree indexing structure for EPLL, and overcome its training tractability challenges in high-dimensional spaces by utilizing special structures of the prior. Experimental results show that our approach accelerates state-of-the-art EPLL-based deconvolution methods by up to 40 times, with very little quality compromise.
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.
Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Yang, J., Zhang, Y., Yin, W.: An efficient TVL1 algorithm for deblurring multichannel images corrupted by impulsive noise. Journal on Scientific Computing 31(4) (2009)
Krishnan, D., Fergus, R.: Fast image deconvolution using hyper-laplacian priors. In: NIPS (2009)
Fergus, R., Singh, B., Hertzmann, A., Roweis, S., Freeman, W.T.: Removing camera shake from a single photograph. In: ToG (SIGGRAPH) (2006)
Roth, S., Blacky, M.: Fields of experts. IJCV 82(2), 205–229 (2009)
Whyte, O., Sivic, J., Zisserman, A.: Deblurring shaken and partially saturated images. In: Proceedings of the IEEE Workshop on Color and Photometry in Computer Vision, with ICCV 2011 (2011)
Cho, S., Wang, J., Lee, S.: Handling outliers in non-blind image deconvolution. In: ICCV (November 2011)
Zoran, D., Weiss, Y.: From learning models of natural image patches to whole image restoration. In: ICCV (2011)
Sun, L., Cho, S., Wang, J., Hays, J.: Edge-based blur kernel estimation using patch priors. In: ICCP (2013)
Jancsary, J., Nowozin, S., Rother, C.: Loss-specific training of non-parametric image restoration models: A new state of the art. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol. 7578, pp. 112–125. Springer, Heidelberg (2012)
Jancsary, J., Nowozin, S., Sharp, T., Rother, C.: Regression Tree Fields - an Efficient, Non-Parametric Approach to Image Labeling Problems. In: CVPR (2012)
Schmidt, U., Rother, C., Nowozin, S., Jancsary, J., Roth, S.: Discriminative non-blind deblurring. In: CVPR (2013)
Zoran, D., Weiss, Y.: Natural images, gaussian mixtures and dead leaves. In: NIPS (2012)
Rhemann, C., Hosni, A., Bleyer, M., Rother, C., Gelautz, M.: Fast cost-volume filtering for visual correspondence and beyond. In: CVPR (2011)
He, K., Sun, J., Tang, X.: Guided image filtering. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 1–14. Springer, Heidelberg (2010)
Köhler, R., Hirsch, M., Mohler, B., Schölkopf, B., Harmeling, S.: Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol. 7578, pp. 27–40. Springer, Heidelberg (2012)
Xu, L., Zheng, S., Jia, J.: Unnatural l0 sparse representation for natural image deblurring. In: CVPR (June 2013)
Cho, S., Lee, S.: Fast motion deblurring. ToG (SIGGRAPH ASIA) 28(5) (2009)
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 (2001)
Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3D transform-domain collaborative filtering. TIP (8) (August 2007)
Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: BM3D image denoising with shape-adaptive principal component analysis. In: SPARS (2009)
Elad, M., Aharon, M.: Image denoising via sparse and redundant representations over learned dictionaries. TIP 15(12), 3736–3745 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, Y., Cho, S., Wang, J., Chang, SF. (2014). Discriminative Indexing for Probabilistic Image Patch Priors. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8692. Springer, Cham. https://doi.org/10.1007/978-3-319-10593-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-10593-2_14
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10592-5
Online ISBN: 978-3-319-10593-2
eBook Packages: Computer ScienceComputer Science (R0)