Advertisement

Single-Image Blind Deblurring for Non-uniform Camera-Shake Blur

  • Yuquan Xu
  • Lu Wang
  • Xiyuan Hu
  • Silong Peng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7726)

Abstract

In this paper we address the problem of estimating latent sharp image and unknown blur kernel from a single motion-blurred image. The blur results from camera shake and is spatially variant. Meanwhile, the blur kernel of motion has three degrees of freedom, i.e., translations and in-plane rotation. In order to solve this problem, we first analyzed the homography blur model for the non-uniform camera-shake blur. We simplified the model to 3-dimensional camera motion which can be accelerated by exploiting the fast Fourier transform to process subsequent image deconvolution. We then proposed an effective method to handle the blind image-deblurring problem by the image decomposition, which does not need to segment the image into local subregions under the assumption of spatially invariant blur. Experimental results on both synthetic and real blurred images show that the presented approach can successfully remove various kinds of blur.

Keywords

Camera Motion Latent Image Motion Blur Blind Deconvolution Blur Kernel 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.: Understanding and evaluating blind deconvolution algorithms. In: CVPR (2009)Google Scholar
  2. 2.
    Joshi, N., Szeliski, R., Kriegman, D.: Psf estimation using sharp edge prediction. In: CVPR (2008)Google Scholar
  3. 3.
    Whyte, O., Sivic, J., Zisserman, A., Ponce, J.: Non-uniform deblurring for shaken images. In: CVPR (2010)Google Scholar
  4. 4.
    Tai, Y., Tan, P., Brown, M.: Richardson-lucy deblurring for scenes under a projective motion path. IEEE Trans. on PAMI 33, 1603–1618 (2011)CrossRefGoogle Scholar
  5. 5.
    Joshi, N., Kang, S., Zitnick, C., Szeliski, R.: Image deblurring using inertial measurement sensors. ACM Trans. Graph. 29, 1–9 (2010)Google Scholar
  6. 6.
    Gupta, A., Joshi, N., Lawrence Zitnick, C., Cohen, M., Curless, B.: Single Image Deblurring Using Motion Density Functions. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 171–184. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  7. 7.
    Hirsch, M., Schuler, C., Harmeling, S., Schölkopf, B.: Fast removal of non-uniform camera shake. In: ICCV (2011)Google Scholar
  8. 8.
    Osher, S., Rudin, L.: Feature-oriented image enhancement using shock filters. SIAM Journal on Numerical Analysis 27, 919–940 (1990)zbMATHCrossRefGoogle Scholar
  9. 9.
    Richardson, W.: Bayesian-based iterative method of image restoration. Journal of the Optical Society of America 62, 55–59 (1972)CrossRefGoogle Scholar
  10. 10.
    Lucy, L.: An iterative technique for the rectification of observed distributions. The Astronomical Journal 79, 745 (1974)CrossRefGoogle Scholar
  11. 11.
    Yuan, L., Sun, J., Quan, L., Shum, H.: Progressive inter-scale and intra-scale non-blind image deconvolution. ACM Trans. Graph. 27 (2008)Google Scholar
  12. 12.
    Krishnan, D., Fergus, R.: Fast image deconvolution using hyper-laplacian priors. In: NIPS, vol. 22 (2009)Google Scholar
  13. 13.
    Chan, T., Wong, C.: Total variation blind deconvolution. IEEE Trans. on Image Processing 7, 370–375 (1998)CrossRefGoogle Scholar
  14. 14.
    Fergus, R., Singh, B., Hertzmann, A., Roweis, S., Freeman, W.: Removing camera shake from a single photograph. ACM Trans. Graph. 25, 787–794 (2006)CrossRefGoogle Scholar
  15. 15.
    Levin, A.: Blind motion deblurring using image statistics. Advances in Neural Information Processing Systems 19, 841 (2007)Google Scholar
  16. 16.
    Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. ACM Trans. Graph. 27, 73:1–73:10 (2008)Google Scholar
  17. 17.
    Cho, S., Lee, S.: Fast motion deblurring. ACM Trans. Graph. 28, 145:1–145:8 (2009)MathSciNetCrossRefGoogle Scholar
  18. 18.
    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
  19. 19.
    Cho, T., Paris, S., Horn, B., Freeman, W.: Blur kernel estimation using the radon transform. In: CVPR (2011)Google Scholar
  20. 20.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.: Efficient marginal likelihood optimization in blind deconvolution. In: CVPR (2011)Google Scholar
  21. 21.
    Wang, C., Sun, L., Cui, P., Zhang, J., Yang, S.: Analyzing image deblurring through three paradigms. IEEE Transactions on Image Processing, 1 (2012)Google Scholar
  22. 22.
    Hirsch, M., Sra, S., Schölkopf, B., Harmeling, S.: Efficient filter flow for space-variant multiframe blind deconvolution. In: CVPR (2010)Google Scholar
  23. 23.
    Harmeling, S., Hirsch, M., Schölkopf, B.: Space-variant single-image blind deconvolution for removing camera shake. In: NIPS (2010)Google Scholar
  24. 24.
    Sorel, M., Sroubek, F.: Space-variant deblurring using one blurred and one underexposed image. In: ICIP (2009)Google Scholar
  25. 25.
    Tai, Y., Du, H., Brown, M., Lin, S.: Image/video deblurring using a hybrid camera. In: CVPR (2008)Google Scholar
  26. 26.
    Tai, Y., Du, H., Brown, M., Lin, S.: Correction of spatially varying image and video motion blur using a hybrid camera. IEEE Trans. on PAMI 32, 1012–1028 (2010)CrossRefGoogle Scholar
  27. 27.
    Ben-Ezra, M., Nayar, S.: Motion-based motion deblurring. IEEE Trans. on PAMI 26, 689–698 (2004)CrossRefGoogle Scholar
  28. 28.
    Shan, Q., Xiong, W., Jia, J.: Rotational motion deblurring of a rigid object from a single image. In: ICCV (2007)Google Scholar
  29. 29.
    Hu, X., Xia, W., Peng, S., Hwang, W.L.: Multiple component predictive coding framework of still images. In: ICME (2011)Google Scholar
  30. 30.
    Liu, R., Jia, J.: Reducing boundary artifacts in image deconvolution. In: ICIP (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Yuquan Xu
    • 1
  • Lu Wang
    • 1
  • Xiyuan Hu
    • 1
  • Silong Peng
    • 1
  1. 1.Institute of AutomationChinese Academy of SciencesBeijingP.R. China

Personalised recommendations