Skip to main content
Log in

Kernel learning for blind image recovery from motion blur

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Restoring image from motion deblur faces great challenges in the estimation of the motion blur kernel that is the key to recover the latent sharp image. In this paper, we present a method to iteratively estimate the structural image and account for the textural component. A scale-aware smoothing operation is developed to remove fine-scale edges with resampling. Our method leverages L0-norm regularization to enforce the sparsity of the motion blur kernel in both intensity and derivative domains. Experiments are conducted to evaluate the performance of our proposed method using two widely accepted public datasets. We found that our proposed method is insensitive to most hyper-parameters. Both qualitative evaluation and quantitative evaluation confirms that our method effectively restores the sharp image without introducing artifacts. The minimum improvements in terms of average PSNR for both datasets are more than 3.13% for all cases and the improvements in terms of average error rate are 15%. By visually comparing the estimated motion blur kernels, it is clear that the estimated kernel by our method is the closest to the actual kernel used to generate the synthesized blurry images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. The fine-scale edge refers to edges of a short length.

References

  1. Cho S, Lee S (2009) Fast motion deblurring. ACM Trans Graph 28(5):145:1–145:8

    Article  Google Scholar 

  2. Cho TS, Paris S, Horn BKP, Freeman WT (2011) Blur kernel estimation using the radon transform. In: IEEE conference on computer vision and pattern recognition, pp 241–248

  3. Fergus R, Singh B, Hertzmann A, Roweis ST, Freeman WT (2006) Removing camera shake from a single photograph. ACM Trans Graph 25(3):787–794

    Article  MATH  Google Scholar 

  4. Gong D, Tan M, Zhang Y, Hengel AVD, Shi Q (2016) Blind image deconvolution by automatic gradient activation. In: IEEE conference on computer vision and pattern recognition, pp 1827–1836

  5. Hirsch M, Schuler CJ, Harmeling S, Schölkopf B (2011) Fast removal of non-uniform camera shake. In: International conference on computer vision, pp 463–470

  6. Köhler R, Hirsch M, Mohler B, Schölkopf B, Harmeling S (2012) Recording and playback of camera shake: Benchmarking blind deconvolution with a real-world database. In: Proceedings of the 12th European Conference on Computer Vision - Volume Part VII, pp 27–40, Florence, Italy

  7. Krishnan D, Tay T, Fergus R (2011) Blind deconvolution using a normalized sparsity measure. In: International conference on computer vision and pattern recognition, pp 233–240

  8. Lai W, Ding J, Lin Y, Chuang Y (2015) Blur kernel estimation using normalized color-line priors. In: IEEE Conference on computer vision and pattern recognition, pp 64–72

  9. Levin A, Weiss Y, Durand F, Freeman WT (2009) Understanding and evaluating blind deconvolution algorithms. In: 2009 IEEE conference on computer vision and pattern recognition, pp 1964–1971

  10. Pan J, Hu Z, Su Z, Yang M (2014) Deblurring text images via l0-regularized intensity and gradient prior. In: IEEE conference on computer vision and pattern recognition, pp 2901–2908

  11. Pan J, Hu Z, Su Z, Yang M (2017) l0 -regularized intensity and gradient prior for deblurring text images and beyond. IEEE Trans Pattern Anal Mach Intell 39(2):342–355

    Article  Google Scholar 

  12. Pan J, Sun D, Pfister H, Yang M (2018) Deblurring images via dark channel prior. IEEE Trans Pattern Anal Mach Intell 40(10):2315–2328

    Article  Google Scholar 

  13. Shan Q, Jia J, Agarwala A (2008) High-quality motion deblurring from a single image. ACM Trans Graph 27(3):73:1–10

    Article  Google Scholar 

  14. Sun L, Cho S, Wang J, Hays J (2013) Edge-based blur kernel estimation using patch priors. In: IEEE international conference on computational photography (ICCP), pp 1–8

  15. Wang W, Yuan X, Wu X, Liu Y (2017) Fast image dehazing method based on linear transformation. IEEE Trans Multimed 19(6):1142–1155

    Article  Google Scholar 

  16. Wang Y, Yang J, Yin W, Zhang Y (2008) A new alternating minimization algorithm for total variation image reconstruction. SIAM Imaging Sciences 1(3):248–272

    Article  MathSciNet  MATH  Google Scholar 

  17. Whyte O, Sivic J, Zisserman A (2011) Deblurring shaken and partially saturated images. In: IEEE international conference on computer vision workshops, pp 745–752

  18. Xu L, Jia J (2010) Two-phase kernel estimation for robust motion deblurring. In: Proceedings of the 11th European conference on computer vision: Part I, pp 157–170

  19. Xu L, Lu C, Xu Y, Jia J (2011) Image smoothing via L0 gradient minimization. ACM Trans Graph 30(6):174–179

    Google Scholar 

  20. Xu L, Zheng S, Jia J (2013) Unnatural l0 sparse representation for natural image deblurring. In: IEEE conference on computer vision and pattern recognition, pp 1107–1114

  21. Yuan X (2010) Segmentation of blurry object by learning from examples. In: Proceedings of SPIE, 7623, 7623–9

  22. Yuan X, Kong L, Feng D, Wei Z (2017) Automatic feature point detection and tracking of human action in time-of-flight videos. IEEE/CAA Journal of Automatica Sinica 4(4):677–685

    Article  Google Scholar 

  23. Yuan X, Li D, Mohapatra D, Elhoseny M (2018) Automatic removal of complex shadows from indoor videos using transfer learning and dynamic thresholding. Comput Electr Eng 70:813–825

    Article  Google Scholar 

  24. Yue T, Cho S, Wang J, Dai Q (2014) Hybrid image deblurring by fusing edge and power spectrum information. In: European conference on computer vision, vol 8695, pp 79–93

Download references

Acknowledgments

The work is partially supported by the National Natural Science Foundation of China (No.61872327, 61472380) and Fundamental Research Funds for the Central Universities (No. JD2017JGPY0011, JZ2017HGBZ0930, PA2018GDQT0011).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Xiaohui Yuan.

Ethics declarations

Conflict of interests

The authors declare no potential conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Qin, F., Fang, S., Wang, L. et al. Kernel learning for blind image recovery from motion blur. Multimed Tools Appl 79, 21873–21887 (2020). https://doi.org/10.1007/s11042-020-09012-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-09012-3

Keywords

Navigation