Robust deblurring based on prediction of informative structure

Zhipeng Cao; Zhenzhong Wei; Guangjun Zhang

Robust deblurring based on prediction of informative structure

View Fulltext

Author(s): Zhipeng Cao ¹ ; Zhenzhong Wei ¹ ; Guangjun Zhang ¹
- Affiliations: 1: Key Laboratory of Precise Opto-Mechatronics Technology, Ministry of Education, School of Instrumentation Science and Opto-electronics Engineering, Beihang University, Beijing 100191, People's Republic of China
Source: Volume 9, Issue 9, September 2015, p. 827 – 835
DOI: 10.1049/iet-ipr.2014.0948 , Print ISSN 1751-9659, Online ISSN 1751-9667

Received 20/08/2014, Accepted 03/01/2015, Published 01/09/2015

This study presents a robust motion deblurring method in which an adaptive prediction is used to extract the informative regions for kernel estimation. The prediction not only sharpens the blurry edges, but also adaptively predicts the large scale structure for kernel estimation. It allows to only use the alternating minimisation with a computationally efficient Gaussian prior for both the image and kernel while without employing thoughtful attention such as multi-scale scheme or kernel refinement. Extensive experiments were carried out to validate the proposed method and to compare it with some previous approaches. The experiment results demonstrated that the approach achieves, if not better than, state-of-the-art results for uniformly blurred images.

References

1. 1)
  - 27. Lucy, L.: ‘An iterative technique for the rectification of observed distributions’, Astron. J., 1974, 79, (6), pp. 745–754 (doi: 10.1086/111605).
2. 2)
  - 30. Zoran, D., Weiss, Y.: ‘From learning models of natural image patches to whole image restoration’. Proc. ICCV, 2011, pp. 479–486.
3. 3)
  - 34. Reeves, S.J.: ‘Fast image restoration without boundary artifacts’, IEEE Trans. Image Process., 2005, 14, (10), pp. 1448–1453 (doi: 10.1109/TIP.2005.854474).
4. 4)
  - 5. Joshi, N., Szeliski, R., Kriegman, D.J.: ‘Psf estimation using sharp edge prediction’. Proc. CVPR, 2008, pp. 1–8.
5. 5)
  - 13. You, Y., Kaveh, M.: ‘Blind image restoration by anisotropic regularization’, IEEE Trans. Image Process., 1999, 8, (3), pp. 396–407 (doi: 10.1109/83.748894).
6. 6)
  - 31. Hu, Z., Yang, M.-H.: ‘Good regions to deblur’. Proc. ECCV, 2012, pp. 59–72.
7. 7)
  - 24. Krishnan, D., Tay, T., Fergus, R.: ‘Blind deconvolution using a normalized sparsity measure’. Proc. CVPR, 2011, pp. 233–240.
8. 8)
  - 1. Xu, L., Jia, J.: ‘Two-phase kernel estimation for robust motion deblurring’. Proc. ECCV, 2010, pp. 157–170.
9. 9)
  - 26. Wang, Y., Yin, W.: ‘Compressed sensing via iterative support detection’. CAAM Technical Report TR09-30, 2009.
10. 10)
  - 4. Shan, Q., Jia, J., Agarwala, A.: ‘High-quality motion deblurring from a single image’, ACM Trans. Graph., 2008, 27, (3), p. 73 (doi: 10.1145/1360612.1360672).
11. 11)
  - 15. Ji, H., Liu, C.: ‘Motion blur identification from image gradients’. Proc. CVPR, 2008, pp. 1–8.
12. 12)
  - 33. Weickert, J.: ‘Coherence-enhancing shock filters’, Lect. Notes Comput. Sci., 2003, 2781, pp. 1–8.
13. 13)
  - 16. Chen, W.G., Nandhakumar, N., Martin, W.N.: ‘Image motion estimation from motion smear – A new computational model’, IEEE Trans. Pattern Anal. Mach. Intell., 1996, 18, (4), pp. 412–425 (doi: 10.1109/34.491622).
14. 14)
  - 8. Sun, L., Cho, S., Wang, J., Hays, J.: ‘Edge-based blur kernel estimation using patch priors’. Proc. IEEE Int. Conf. on Computational Photography (ICCP), April 2013, pp. 1–8.
15. 15)
  - 18. Cho, S., Matsushita, Y., Lee, S.: ‘Removing non-uniform motion blur from images’. Proc. ICCV, 2007, pp. 1–8.
16. 16)
  - 36. Sun, L., Hays, J.: ‘Super-resolution from internet-scale scene matching’. Proc. ICCP, 2012.
17. 17)
  - 20. Ben-Ezra, M., Nayar, S.K.: ‘Motion-based motion deblurring’, IEEE Trans. Pattern Anal. Mach. Intell., 2004, 26, (6), pp. 689–698 (doi: 10.1109/TPAMI.2004.1).
18. 18)
  - 12. Yitzhaky, Y., Mor, I., Lantzman, A., Kopeika, N.S.: ‘Direct method for restoration of motion-blurred images’, J. Opt. Soc. Am. A., 1998, 15, (6), pp. 1512–1519 (doi: 10.1364/JOSAA.15.001512).
19. 19)
  - 7. Cai, J.F., Ji, H., Liu, C., Shen, Z.: ‘Blind motion deblurring from a single image using sparse approximation’. Proc. CVPR, 2009, pp. 104–111.
20. 20)
  - 10. Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: ‘Understanding and evaluating blind deconvolution algorithms’. Proc. CVPR, 2009, pp. 1964–1971.
21. 21)
  - 32. Osher, S., Rudin, L.: ‘Feature-oriented image enhancement using shock filters’, SIAM J. Numer. Anal., 1990, 27, pp. 919–940 (doi: 10.1137/0727053).
22. 22)
  - 22. Levin, A., Sand, P., Cho, T.S., Durand, F., Freeman, W.T.: ‘Motion-invariant photography’, ACM Trans. Graphics, 2008, 27, (3), p. 71 (doi: 10.1145/1360612.1360670).
23. 23)
  - 21. Tai, Y.W., Du, H., Brown, M.S., Lin, S.: ‘Image/video deblurring using a hybrid camera’. Proc. CVPR, 2008, pp. 1–8.
24. 24)
  - 9. Xu, L., Zheng, S., Jia, J.: ‘Unnatural L0 sparse representation for natural image deblurring’. Proc. CVPR, 2013, pp. 1107–1114.
25. 25)
  - 17. Rav-Acha, A., Peleg, S.: ‘Two motion-blurred images are better than one’, Pattern Recogn. Lett., 2005, 26, pp. 311–317 (doi: 10.1016/j.patrec.2004.10.017).
26. 26)
  - 14. Dai, S., Wu, Y.: ‘Motion from blur’. Proc. CVPR, 2008, pp. 1–8.
27. 27)
  - 25. Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: ‘Efficient marginal likelihood optimization in blind deconvolution’. Proc. CVPR, 2011, pp. 2657–2664.
28. 28)
  - 11. Money, J.H., Kang, S.H.: ‘Total variation minimizing blind deconvolution with shock filter reference’, Image Vis. Comput., 2008, 26, (2), pp. 302–314 (doi: 10.1016/j.imavis.2007.06.005).
29. 29)
  - 35. Koehler, R., Hirsch, M., Harmeling, S., Mohler, B., Scholkopf, B.: ‘Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database’. Proc. ECCV, 2012, pp. 27–40.
30. 30)
  - 6. Cho, S., Lee, S.: ‘Fast motion deblurring’, ACM Trans. Graph., 2009, 28, (5), p. 145 (doi: 10.1145/1618452.1618491).
31. 31)
  - 23. Levin, A., Fergus, R., Durand, F., Freeman, W.T.: ‘Image and depth from a conventional camera with a coded aperture’, ACM Trans. Graphics, 2007, 26, (3) p. 70 (doi: 10.1145/1276377.1276464).
32. 32)
  - 3. Jia, J.: ‘Single image motion deblurring using transparency’. Proc. CVPR, 2007, pp. 1–8.
33. 33)
  - 29. Yuan, L., Sun, J., Quan, L., Shum, H.Y.: ‘Progressive inter-scale and intra-scale non-blind image deconvolution’, ACM Trans. Graphics, 2008, 27, (3), p. 74 (doi: 10.1145/1360612.1360673).
34. 34)
  - 19. Yuan, L., Sun, J., Quan, L., Shum, H.Y.: ‘Image deblurring with blurred/noisy image pairs’, ACM Trans. Graphics, 2007, 26, (3), p. 1 (doi: 10.1145/1276377.1276379).
35. 35)
  - 2. Fergus, R., Singh, B., Hertzmann, A., Roweis, S.T., Freeman, W.T.: ‘Removing camera shake from a single photograph’, ACM Trans. Graph., 2006, 25, (3), pp. 787–794 (doi: 10.1145/1141911.1141956).
36. 36)
  - 28. Wiener, N.: ‘Extrapolation, interpolation, and smoothing of stationary time series’ (MIT Press, 1964).

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Robust deblurring based on prediction of informative structure

References

Related content