Advertisement

Blind Image Deblurring Using Elastic-Net Based Rank Prior

  • Hongyan Wang
  • Jinshan Pan
  • Zhixun SuEmail author
  • Songxin Liang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10116)

Abstract

In this paper, we propose a new image prior for blind image deblurring. The proposed prior exploits similar patches of an image and it is based on an elastic-net regularization of singular values. We quantitatively verify that it favors clear images over blurred images. This property is able to facilitate the kernel estimation in the conventional maximum a posterior framework. Based on this prior, we develop an efficient optimization method to solve the proposed model. The proposed method does not require any complex filtering strategies to select salient edges which are critical to the state-of-the-art deblurring algorithms. Quantitative and qualitative experimental evaluations demonstrate that the proposed algorithm performs favorably against the state-of-the-art deblurring methods.

Keywords

Kernel Estimation Clear Image Image Denoising Nuclear Norm Recovered Image 
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.

Notes

Acknowledgements

This work has been partially supported by National Natural Science Foundation of China (No. 61572099, 51379033, and 51522902) and National Science and Technology Major Project (No. ZX20140419 and 2014ZX04001011).

Supplementary material

426013_1_En_1_MOESM1_ESM.zip (26.4 mb)
Supplementary material 1 (zip 27003 KB)

References

  1. 1.
    Fergus, R., Singh, B., Hertzmann, A., Roweis, S.T., Freeman, W.T.: Removing camera shake from a single photograph. ACM Trans. Graph. 25, 787–794 (2006)CrossRefGoogle Scholar
  2. 2.
    Levin, A., Fergus, R., Durand, F., Freeman, W.T.: Image and depth from a conventional camera with a coded aperture. ACM Trans. Graph. 26, 70 (2007)CrossRefGoogle Scholar
  3. 3.
    Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. ACM Trans. Graph. 27, 73 (2008)Google Scholar
  4. 4.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Understanding and evaluating blind deconvolution algorithms. In: CVPR, pp. 1964–1971 (2009)Google Scholar
  5. 5.
    Krishnan, D., Tay, T., Fergus, R.: Blind deconvolution using a normalized sparsity measure. In: CVPR, pp. 233–240 (2011)Google Scholar
  6. 6.
    Michaeli, T., Irani, M.: Blind deblurring using internal patch recurrence. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 783–798. Springer, Cham (2014). doi: 10.1007/978-3-319-10578-9_51 Google Scholar
  7. 7.
    Pan, J., Sun, D., Pfister, H., Yang, M.H.: Blind image deblurring using dark channel prior. In: CVPR (2016)Google Scholar
  8. 8.
    Cho, S., Lee, S.: Fast motion deblurring. ACM Trans. Graph. 28, 145 (2009)CrossRefGoogle Scholar
  9. 9.
    Xu, L., Jia, J.: Two-phase kernel estimation for robust motion deblurring. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 157–170. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-15549-9_12 CrossRefGoogle Scholar
  10. 10.
    Xu, L., Zheng, S., Jia, J.: Unnatural l0 sparse representation for natural image deblurring. In: CVPR, pp. 1107–1114 (2013)Google Scholar
  11. 11.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Efficient marginal likelihood optimization in blind deconvolution. In: CVPR, pp. 2657–2664 (2011)Google Scholar
  12. 12.
    Money, J.H., Kang, S.H.: Total variation minimizing blind deconvolution with shock filter reference. Image Vis. Comput. 26, 302–314 (2008)CrossRefGoogle Scholar
  13. 13.
    Sun, L., Cho, S., Wang, J., Hays, J.: Edge-based blur kernel estimation using patch priors. In: ICCP, pp. 1–8 (2013)Google Scholar
  14. 14.
    Hacohen, Y., Shechtman, E., Lischinski, D.: Deblurring by example using dense correspondence. In: ICCV, pp. 2384–2391 (2013)Google Scholar
  15. 15.
    Pan, J., Hu, Z., Su, Z., Yang, M.H.: Deblurring text images via l0-regularized intensity and gradient prior. In: CVPR, pp. 2901–2908 (2014)Google Scholar
  16. 16.
    Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: CVPR, pp. 60–65 (2005)Google Scholar
  17. 17.
    Dong, W., Shi, G., Li, X.: Nonlocal image restoration with bilateral variance estimation: a low-rank approach. IEEE Trans. Image Process. 22, 700–711 (2013)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Gu, S., Zhang, L., Zuo, W., Feng, X.: Weighted nuclear norm minimization with application to image denoising. In: CVPR, pp. 2862–2869 (2014)Google Scholar
  19. 19.
    Xu, J., Zhang, L., Zuo, W., Zhang, D., Feng, X.: Patch group based nonlocal self-similarity prior learning for image denoising. In: ICCV, pp. 244–252 (2015)Google Scholar
  20. 20.
    Cai, J.F., Candès, E.J., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20, 1956–1982 (2010)MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Ren, W., Cao, X., Pan, J., Guo, X., Zuo, W., Yang, M.: Image deblurring via enhanced low-rank prior. IEEE Trans. Image Process. 25, 3426–3437 (2016)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Kim, E., Lee, M., Oh, S.: Elastic-net regularization of singular values for robust subspace learning. In: CVPR, pp. 915–923 (2015)Google Scholar
  23. 23.
    Wang, S., Zhang, L., Liang, Y.: Nonlocal spectral prior model for low-level vision. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7726, pp. 231–244. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-37431-9_18 CrossRefGoogle Scholar
  24. 24.
    Geman, D., Reynolds, G.: Constrained restoration and the recovery of discontinuities. IEEE Trans. Pattern Anal. Mach. Intell. 14, 367–383 (1992)CrossRefGoogle Scholar
  25. 25.
    Geman, D., Yang, C.: Nonlinear image recovery with half-quadratic regularization. IEEE Trans. Image Process. 4, 932–946 (1995)CrossRefGoogle Scholar
  26. 26.
    Perrone, D., Favaro, P.: Total variation blind deconvolution: the devil is in the details. In: CVPR, pp. 2909–2916 (2014)Google Scholar
  27. 27.
    Hu, Z., Yang, M.-H.: Good regions to deblur. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 59–72. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33715-4_5 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Hongyan Wang
    • 1
  • Jinshan Pan
    • 1
  • Zhixun Su
    • 1
    Email author
  • Songxin Liang
    • 1
  1. 1.School of Mathematical SciencesDalian University of TechnologyDalianChina

Personalised recommendations