Advertisement

Debluring Low-Resolution Images

  • Jinshan PanEmail author
  • Zhe Hu
  • Zhixun Su
  • Ming-Hsuan Yang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10116)

Abstract

The recent years have witnessed significant advances in image deblurring. In general, the success of deblurring methods depends heavily on extraction of salient structures from a blurry image for kernel estimation. Most deblurring methods often operate on high-resolution images where contours or edges can be extracted for kernel estimation. However, recovering reliable structures from low-resolution images becomes extremely challenging. In this paper, we propose a spatially variant deblurring algorithm for low-resolution images based on the exemplars. To exploit the exemplar information, we develop a super-resolution guided method to help the restoration of reliable image structures which can be used for kernel estimation. Experimental evaluations against the state-of-the-art methods show that the proposed algorithm performs favorably in deblurring low-resolution images. Furthermore, we show that the SR results obtained as byproducts in our method are comparable compared to other blind SR methods.

Keywords

Camera Motion Latent Image Kernel Estimation Super Resolution 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.

Notes

Acknowledgements

This work has been supported in part by NSF CAREER (No. 1149783), NSF IIS (No. 1152576), NSFC (No. 61572099 and 61320106008) and a gift from Adobe.

Supplementary material

426013_1_En_8_MOESM1_ESM.zip (77.4 mb)
Supplementary material 1 (zip 79272 KB)

References

  1. 1.
    Sroubek, F., Cristóbal, G., Flusser, J.: A unified approach to superresolution and multichannel blind deconvolution. IEEE TIP 16, 2322–2332 (2007)MathSciNetGoogle Scholar
  2. 2.
    Xu, L., Zheng, S., Jia, J.: Unnatural L\(_0\) sparse representation for natural image deblurring. In: CVPR, pp. 1107–1114 (2013)Google Scholar
  3. 3.
    Fergus, R., Singh, B., Hertzmann, A., Roweis, S.T., Freeman, W.T.: Removing camera shake from a single photograph. ACM TOG 25, 787–794 (2006)CrossRefGoogle Scholar
  4. 4.
    Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. ACM TOG 27, 73 (2008)Google Scholar
  5. 5.
    Cho, S., Lee, S.: Fast motion deblurring. ACM TOG 28, 145 (2009)CrossRefGoogle Scholar
  6. 6.
    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
  7. 7.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Efficient marginal likelihood optimization in blind deconvolution. In: CVPR, pp. 2657–2664 (2011)Google Scholar
  8. 8.
    Krishnan, D., Tay, T., Fergus, R.: Blind deconvolution using a normalized sparsity measure. In: CVPR, pp. 2657–2664 (2011)Google Scholar
  9. 9.
    Goldstein, A., Fattal, R.: Blur-Kernel estimation from spectral irregularities. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 622–635. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33715-4_45 CrossRefGoogle Scholar
  10. 10.
    Yuan, L., Sun, J., Quan, L., Shum, H.: Image deblurring with blurred/noisy image pairs. ACM TOG 26, 1 (2007)CrossRefGoogle Scholar
  11. 11.
    Jia, J.: Mathematical Models and Practical Solvers for Uniform Motion Deblurring. Cambridge University Press, Cambridge (2014)CrossRefGoogle Scholar
  12. 12.
    Lee, S., Cho, S.: Recent advances in image deblurring. In: SIGGRAPH Asia 2013 Course (2013)Google Scholar
  13. 13.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Understanding and evaluating blind deconvolution algorithms. In: CVPR, pp. 1964–1971 (2009)Google Scholar
  14. 14.
    Lou, Y., Bertozzi, A.L., Soatto, S.: Direct sparse deblurring. J. Math. Imaging Vis. 39, 1–12 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Zhang, H., Yang, J., Zhang, Y., Huang, T.S.: Sparse representation based blind image deblurring. In: ICME, pp. 1–6 (2011)Google Scholar
  16. 16.
    Cai, J.F., Ji, H., Liu, C., Shen, Z.: Framelet based blind motion deblurring from a single image. IEEE TIP 21, 562–572 (2012)MathSciNetGoogle Scholar
  17. 17.
    Zoran, D., Weiss, Y.: From learning models of natural image patches to whole image restoration. In: ICCV, pp. 479–486 (2011)Google Scholar
  18. 18.
    Roth, S., Black, M.J.: Fields of experts: a framework for learning image priors. In: CVPR, pp. 860–867 (2005)Google Scholar
  19. 19.
    Takeda, H., Farsiu, S., Milanfar, P.: Deblurring using regularized locally adaptive Kernel regression. IEEE TIP 17, 550–563 (2008)MathSciNetGoogle Scholar
  20. 20.
    Sun, L., Cho, S., Wang, J., Hays, J.: Good image priors for non-blind deconvolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 231–246. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-10593-2_16 Google Scholar
  21. 21.
    Zhang, H., Wipf, D.P., Zhang, Y.: Multi-image blind deblurring using a coupled adaptive sparse prior. In: CVPR, pp. 1051–1058 (2013)Google Scholar
  22. 22.
    Zhang, H., Wipf, D.P.: Non-uniform camera shake removal using a spatially-adaptive sparse penalty. In: NIPS, pp. 1556–1564 (2013)Google Scholar
  23. 23.
    Perrone, D., Favaro, P.: Total variation blind deconvolution: the devil is in the details. In: CVPR, pp. 2909–2916 (2014)Google Scholar
  24. 24.
    Joshi, N., Szeliski, R., Kriegman, D.J.: PSF estimation using sharp edge prediction. In: CVPR (2008)Google Scholar
  25. 25.
    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. LNCS, vol. 7578, pp. 27–40. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33786-4_3 CrossRefGoogle Scholar
  26. 26.
    Sun, L., Cho, S., Wang, J., Hays, J.: Edge-based blur kernel estimation using patch priors. In: ICCP (2013)Google Scholar
  27. 27.
    HaCohen, Y., Shechtman, E., Lischinski, D.: Deblurring by example using dense correspondence. In: ICCV, pp. 2384–2391 (2013)Google Scholar
  28. 28.
    Pan, J., Hu, Z., Su, Z., Yang, M.-H.: Deblurring face images with exemplars. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 47–62. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-10584-0_4 Google Scholar
  29. 29.
    Tai, Y., Tan, P., Brown, M.S.: Richardson-Lucy deblurring for scenes under a projective motion path. IEEE PAMI 33, 1603–1618 (2011)CrossRefGoogle Scholar
  30. 30.
    Whyte, O., Sivic, J., Zisserman, A., Ponce, J.: Non-uniform deblurring for shaken images. IJCV 98, 168–186 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  31. 31.
    Gupta, A., Joshi, N., Zitnick, C.L., Cohen, M.F., Curless, B.: Single image deblurring using motion density functions. In: ECCV, pp. 171–184 (2010)Google Scholar
  32. 32.
    Hirsch, M., Schuler, C.J., Harmeling, S., Schölkopf, B.: Fast removal of non-uniform camera shake. In: ICCV, pp. 463–470 (2011)Google Scholar
  33. 33.
    Harmeling, S., Hirsch, M., Schölkopf, B.: Space-variant single-image blind deconvolution for removing camera shake. In: NIPS, pp. 829–837 (2010)Google Scholar
  34. 34.
    Kim, T.H., Ahn, B., Lee, K.M.: Dynamic scene deblurring. In: ICCV, pp. 3160–3167 (2013)Google Scholar
  35. 35.
    Kim, T.H., Lee, K.M.: Segmentation-free dynamic scene deblurring. In: CVPR, pp. 2766–2773 (2014)Google Scholar
  36. 36.
    Chakrabarti, A., Zickler, T., Freeman, W.T.: Analyzing spatially-varying blur. In: CVPR, pp. 2512–2519 (2010)Google Scholar
  37. 37.
    Harmeling, S., Sra, S., Hirsch, M., Schölkopf, B.: Multiframe blind deconvolution, super-resolution, and saturation correction via incremental EM. In: ICIP, pp. 3313–3316 (2010)Google Scholar
  38. 38.
    Michaeli, T., Irani, M.: Nonparametric blind super-resolution. In: ICCV, pp. 945–952 (2013)Google Scholar
  39. 39.
    Yang, C.Y., Yang, M.H.: Fast direct super-resolution by simple functions. In: ICCV, pp. 561–568 (2013)Google Scholar
  40. 40.
    Pan, J., Hu, Z., Su, Z., Yang, M.H.: Deblurring text images via L\(_0\)-regularized intensity and gradient prior. In: CVPR, pp. 2901–2908 (2014)Google Scholar
  41. 41.
    Levin, A., Fergus, R., Durand, F., Freeman, W.T.: Image and depth from a conventional camera with a coded aperture. ACM TOG 26, 70 (2007)CrossRefGoogle Scholar
  42. 42.
    Zhang, H., Yang, J., Zhang, Y., Huang, T.S.: Close the loop: joint blind image restoration and recognition with sparse representation prior. In: ICCV, pp. 770–777 (2011)Google Scholar
  43. 43.
    Hu, Z., Huang, J.B., Yang, M.H.: Single image deblurring with adaptive dictionary learning. In: ICIP, pp. 1169–1172 (2010)Google Scholar
  44. 44.
    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, Heidelberg (2014). doi: 10.1007/978-3-319-10578-9_51 Google Scholar
  45. 45.
    Cho, S., Wang, J., Lee, S.: Video deblurring for hand-held cameras using patch-based synthesis. ACM TOG 31, 64:1–64:9 (2012)CrossRefGoogle Scholar
  46. 46.
    Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: ICCV, pp. 349–356 (2009)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Jinshan Pan
    • 1
    Email author
  • Zhe Hu
    • 2
  • Zhixun Su
    • 1
  • Ming-Hsuan Yang
    • 2
  1. 1.Dalian University of TechnologyDalianChina
  2. 2.University of CaliforniaMercedUSA

Personalised recommendations