Motion Deblurring Using Super-Sparsity

  • Jingxiong Zhao
  • Haohua Zhao
  • Keting Zhang
  • Liqing Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8228)


Motion blur is caused by the camera shake during the exposure in which the blur kernel describes the trace of shaking. Based on this generating process of the kernel , we observed that the distribution of the kernel obeys super-sparsity, as the natural images. Recent works mostly exploit various kinds of priors in their models, but focus on the the speed or a close-form formulation for convenience of mathematical calculation ignoring the intrinsic feature of the kernels and images. In this paper we propose a new model with super-sparse prior for the deblurring problem from one single image. Since the close-form formulation of this model doesn’t exist, we use a look-up table trick to approximate the solution. Qualitative and quantitative evaluation demonstrate that our model with super-sparse prior can produce stable and high-quality results.


Motion Deblur Blind Deconvolution Super-sparsity 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fergus, R., Singh, B., Hertzmann, A., Rowels, S.T., Freeman, W.T.: Removing camera shake from a single photograph. In: ACM SIGGRAPH, pp. 787–794 (2006)Google Scholar
  2. 2.
    Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. In: ACM SIGGRAPH, pp. 73:1–73:10 (2008)Google Scholar
  3. 3.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Understanding and evaluating blind deconvolution algorithm. In: CVPR, pp. 1964–1971 (2009)Google Scholar
  4. 4.
    Cho, S., Lee, S.: Fast motion deblurring. ACM Trans. Graph. 28 (2009)Google Scholar
  5. 5.
    Joshi, N., Szeliski, R., Kriegman, D.J.: PSF estimation using sharp edge prediction. In: CVPR (2007)Google Scholar
  6. 6.
    Kundur, D., Hatzinakos, D.: Blind image deconvolution. SPMag 13(3), 43–64 (1996)Google Scholar
  7. 7.
    You, Y.-L., Kaveh, M.: Blind image restoration by anisotropic regularization. IEEE Transactions on Image Processing 8, 396–407 (1999)CrossRefGoogle Scholar
  8. 8.
    Yitzhaky, Y., Mor, I.: Direct method for restoration of motion-blurred images. Journal of Opt. Soc. Am. A 15(6), 1512–1519 (1998)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, Part I. LNCS, vol. 6311, pp. 157–170. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  10. 10.
    Hu, Z., Yang, M.-H.: Good regions to deblur. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 59–72. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  11. 11.
    Bar, L., Sochen, N., Kiryati, N.: Image deblurring in the presence of salt-and-pepper noise. In: Kimmel, R., Sochen, N.A., Weickert, J. (eds.) Scale-Space 2005. LNCS, vol. 3459, pp. 107–118. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  12. 12.
    Wang, Y., Yang, J., Yin, W., Zhang, Y.: A new alternating minimization algorithm for total variation image reconstruction. SIAM J. Image Sciences 1(3), 248–272 (2008)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Jingxiong Zhao
    • 1
  • Haohua Zhao
    • 1
  • Keting Zhang
    • 1
  • Liqing Zhang
    • 1
  1. 1.MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems, Department of Computer Science and EngineeringShanghai Jiao Tong UniversityChina

Personalised recommendations