Good Image Priors for Non-blind Deconvolution

Generic vs. Specific
  • Libin Sun
  • Sunghyun Cho
  • Jue Wang
  • James Hays
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8692)


Most image restoration techniques build “universal” image priors, trained on a variety of scenes, which can guide the restoration of any image. But what if we have more specific training examples, e.g. sharp images of similar scenes? Surprisingly, state-of-the-art image priors don’t seem to benefit from from context-specific training examples. Re-training generic image priors using ideal sharp example images provides minimal improvement in non-blind deconvolution. To help understand this phenomenon we explore non-blind deblurring performance over a broad spectrum of training image scenarios. We discover two strategies that become beneficial as example images become more context-appropriate: (1) locally adapted priors trained from region level correspondence significantly outperform globally trained priors, and (2) a novel multi-scale patch-pyramid formulation is more successful at transferring mid and high frequency details from example scenes. Combining these two key strategies we can qualitatively and quantitatively outperform leading generic non-blind deconvolution methods when context-appropriate example images are available. We also compare to recent work which, like ours, tries to make use of context-specific examples.


deblur non-blind deconvolution gaussian mixtures image pyramid image priors camera shake 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cho, S., Lee, S.: Fast motion deblurring. ACM Transactions on Graphics (2009)Google Scholar
  2. 2.
    Cho, T.S., Joshi, N., Zitnick, C.L., Kang, S.B., Szeliski, R., Freeman, W.T.: A content-aware image prior. In: CVPR (2010)Google Scholar
  3. 3.
    Cho, T.S., Zitnick, C.L., Joshi, N., Kang, S.B., Szeliski, R., Freeman, W.T.: Image restoration by matching gradient distributions. IEEE Transactions on Pattern Analysis and Machine Intelligence (2012)Google Scholar
  4. 4.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
  5. 5.
    Fergus, R., Singh, B., Hertzmann, A., Roweis, S.T., Freeman, W.T.: Removing camera shake from a single photograph. ACM Transactions on Graphics (2006)Google Scholar
  6. 6.
    HaCohen, Y., Shechtman, E., Goldman, D., Lischinski, D.: Non-rigid dense correspondence with applications for image enhancement. ACM Transactions on Graphics (2011)Google Scholar
  7. 7.
    HaCohen, Y., Shechtman, E., Lischinski, D.: Deblurring by example using dense correspondence. In: ICCV (2013)Google Scholar
  8. 8.
    Hays, J., Efros, A.A.: Im2gps: estimating geographic information from a single image. In: CVPR (2008)Google Scholar
  9. 9.
    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
  10. 10.
    Krishnan, D., Fergus, R.: Fast image deconvolution using hyper-laplacian priors. In: NIPS (2009)Google Scholar
  11. 11.
    Levi, E.: Using Natural Image Priors: Maximizing Or Sampling? Hebrew University of Jerusalem (2009),
  12. 12.
    Levin, A., Fergus, R., Durand, F., Freeman, W.T.: Image and depth from a conventional camera with a coded aperture. ACM Transactions on Graphics (2007)Google Scholar
  13. 13.
    Levin, A., Nadler, B., Durand, F., Freeman, W.T.: Patch complexity, finite pixel correlations and optimal denoising. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 73–86. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  14. 14.
    Levin, A., Weiss, Y.: User assisted separation of reflections from a single image using a sparsity prior. TPAMI (2007)Google Scholar
  15. 15.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Understanding and evaluating blind deconvolution algorithms. In: CVPR (2009)Google Scholar
  16. 16.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Efficient marginal likelihood optimization in blind deconvolution. In: CVPR (2011)Google Scholar
  17. 17.
    Roth, S., Black, M.J.: Fields of experts: A framework for learning image priors. In: CVPR (2005)Google Scholar
  18. 18.
    Schmidt, U., Rother, C., Nowozin, S., Jancsary, J., Roth, S.: Discriminative non-blind deblurring. In: CVPR (2013)Google Scholar
  19. 19.
    Schuler, C., Burger, H., Harmeling, S., Schölkopf, B.: A machine learning approach for non-blind image deconvolution. In: CVPR (2013)Google Scholar
  20. 20.
    Sun, L., Cho, S., Wang, J., Hays, J.: Edge-based blur kernel estimation using patch priors. In: ICCP (2013)Google Scholar
  21. 21.
    Weiss, Y., Freeman, W.T.: What makes a good model of natural images? In: CVPR (2007)Google Scholar
  22. 22.
    Xu, L., Jia, J.: Two-phase kernel estimation for robust motion deblurring. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 157–170. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  23. 23.
    Yu, G., Sapiro, G., Mallat, S.: Solving inverse problems with piecewise linear estimators: From gaussian mixture models to structured sparsity. Transactions on Image Processing (2012)Google Scholar
  24. 24.
    Yue, H., Sun, X., Yang, J., Wu, F.: Landmark image super-resolution by retrieving web images. IEEE Transactions on Image Processing (2013)Google Scholar
  25. 25.
    Zoran, D., Weiss, Y.: From learning models of natural image patches to whole image restoration. In: ICCV (2011)Google Scholar
  26. 26.
    Zuo, W., Zhang, L., Song, C., Zhang, D.: Texture enhanced image denoising via gradient histogram preservation. In: CVPR (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Libin Sun
    • 1
  • Sunghyun Cho
    • 2
  • Jue Wang
    • 2
  • James Hays
    • 1
  1. 1.Brown UniversityProvidenceUSA
  2. 2.Adobe ResearchSeattleUSA

Personalised recommendations