Discriminative Indexing for Probabilistic Image Patch Priors

  • Yan Wang
  • Sunghyun Cho
  • Jue Wang
  • Shih-Fu Chang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8692)


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.


Gaussian Mixture Model Markov Random Field Image Patch Conditional Random Field Tree Depth 
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.


  1. 1.
    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)Google Scholar
  2. 2.
    Krishnan, D., Fergus, R.: Fast image deconvolution using hyper-laplacian priors. In: NIPS (2009)Google Scholar
  3. 3.
    Fergus, R., Singh, B., Hertzmann, A., Roweis, S., Freeman, W.T.: Removing camera shake from a single photograph. In: ToG (SIGGRAPH) (2006)Google Scholar
  4. 4.
    Roth, S., Blacky, M.: Fields of experts. IJCV 82(2), 205–229 (2009)CrossRefGoogle Scholar
  5. 5.
    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)Google Scholar
  6. 6.
    Cho, S., Wang, J., Lee, S.: Handling outliers in non-blind image deconvolution. In: ICCV (November 2011)Google Scholar
  7. 7.
    Zoran, D., Weiss, Y.: From learning models of natural image patches to whole image restoration. In: ICCV (2011)Google Scholar
  8. 8.
    Sun, L., Cho, S., Wang, J., Hays, J.: Edge-based blur kernel estimation using patch priors. In: ICCP (2013)Google Scholar
  9. 9.
    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)CrossRefGoogle Scholar
  10. 10.
    Jancsary, J., Nowozin, S., Sharp, T., Rother, C.: Regression Tree Fields - an Efficient, Non-Parametric Approach to Image Labeling Problems. In: CVPR (2012)Google Scholar
  11. 11.
    Schmidt, U., Rother, C., Nowozin, S., Jancsary, J., Roth, S.: Discriminative non-blind deblurring. In: CVPR (2013)Google Scholar
  12. 12.
    Zoran, D., Weiss, Y.: Natural images, gaussian mixtures and dead leaves. In: NIPS (2012)Google Scholar
  13. 13.
    Rhemann, C., Hosni, A., Bleyer, M., Rother, C., Gelautz, M.: Fast cost-volume filtering for visual correspondence and beyond. In: CVPR (2011)Google Scholar
  14. 14.
    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)CrossRefGoogle Scholar
  15. 15.
    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)CrossRefGoogle Scholar
  16. 16.
    Xu, L., Zheng, S., Jia, J.: Unnatural l0 sparse representation for natural image deblurring. In: CVPR (June 2013)Google Scholar
  17. 17.
    Cho, S., Lee, S.: Fast motion deblurring. ToG (SIGGRAPH ASIA) 28(5) (2009)Google Scholar
  18. 18.
    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)Google Scholar
  19. 19.
    Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3D transform-domain collaborative filtering. TIP (8) (August 2007)Google Scholar
  20. 20.
    Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: BM3D image denoising with shape-adaptive principal component analysis. In: SPARS (2009)Google Scholar
  21. 21.
    Elad, M., Aharon, M.: Image denoising via sparse and redundant representations over learned dictionaries. TIP 15(12), 3736–3745 (2006)MathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Yan Wang
    • 1
  • Sunghyun Cho
    • 2
  • Jue Wang
    • 2
  • Shih-Fu Chang
    • 1
  1. 1.Dept. of Electrical EngineeringColumbia UniversityUSA
  2. 2.Adobe ResearchUSA

Personalised recommendations