Blind Image Deblurring Using Dark Channel Prior

Jinshan Pan    Deqing Sun     Hanspeter Pfister     Ming-Hsuan Yang


Real captured image Deblurrred result Dark channel of the input image Dark channel of the output image

Abstract

We present a simple and effective blind image deblurring method based on the dark channel prior. Our work is inspired by the interesting observation that the dark channel of blurred images is less sparse. While most image patches in the clean image contain some dark pixels, these pixels are not dark when averaged with neighboring highintensity pixels during the blur process. This change in the sparsity of the dark channel is an inherent property of the blur process, which we both prove mathematically and validate using training data. Therefore, enforcing the sparsity of the dark channel helps blind deblurring on various scenarios, including natural, face, text, and low-illumination images. However, sparsity of the dark channel introduces a non-convex non-linear optimization problem. We introduce a linear approximation of the min operator to compute the dark channel. Our look-up-table-based method converges fast in practice and can be directly extended to non-uniform deblurring. Extensive experiments show that our method achieves state-of-the-art results on deblurring natural images and compares favorably methods that are well-engineered for specific scenarios.



Technical Papers and Codes

Jinshan Pan, Deqing Sun, Hanspeter Pfister, and Ming-Hsuan Yang, "Blind Image Deblurring Using Dark Channel Prior", IEEE International Conference on Computer Vision (CVPR), 2016 (Oral presentation)

    Paper      

    Supplemental material   

    MATLAB code   


Bibtex

        @InProceedings{Pan_2016_CVPR,
        Title                    = {Blind Image Deblurring Using Dark Channel Prior},
        Author                   = {Pan, Jinshan and Sun, Deqing and Pfister, Hanspeter and Yang, Ming-Hsuan},
        Booktitle                = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
        Year                     = {2016},
        Month                    = {June}
        }


Experimental Results

More results are included in supplemental material.


Natural image deblurring

Blurred image Xu et al. CVPR 2013 Pan et al. CVPR 2014 Ours
Blurred image Cho and Lee Siggraph Asia 2009 Xu and Jia ECCV 2010 Ours

Text image deblurring

Blurred image Xu et al. CVPR 2013 Pan et al. CVPR 2014 Ours
Blurred image Xu et al. CVPR 2013 Pan et al. CVPR 2014 Ours

Low-illumination image deblurring

Blurred image Xu et al. CVPR 2013 Hu et al. CVPR 2014 Ours
Blurred image Xu et al. CVPR 2013 He et al. CVPR 2014 Ours

Face image deblurring

Blurred image Xu et al. CVPR 2013 Pan et al. ECCV 2014 Ours
Blurred image Xu et al. CVPR 2013 Pan et al. ECCV 2014 Ours

Non-uniform image deblurring

Blurred image Whyte et al. IJCV 2012 Xu et al. CVPR 2013 Ours
Blurred image Gupta et al. ECCV 2010 Xu et al. CVPR 2013 Ours



Quantitative Evaluation on Natural Image Deblurring Datasets

Results on Levin et al. CVPR 2009's dataset Results on Köhler et al. ECCV 2012's dataset Results on Sun et al. ICCP 2013's dataset




References

[1] S. Cho and S. Lee. “Fast motion deblurring”, SIGGRAPH ASIA 2009.

[2] L. Xu and J. Jia. “Two-phase kernel estimation for robust motion deblurring”, ECCV 2010.

[3] L. Xu, S. Zheng, and J. Jia. “Unnatural L0 sparse representation for natural image deblurring”, CVPR 2013.

[4] J. Pan, Z. Hu, Z. Su, and M.-H. Yang. “Deblurring text images via L0-regularized intensity and gradient prior”, CVPR 2014.

[5] Z. Hu, S. Cho, J. Wang, and M.-H. Yang. “Deblurring low-light images with light streaks”, CVPR 2014.

[6] J. Pan, Z. Hu, Z. Su, and M.-H. Yang. “Deblurring face images with exemplars”, ECCV 2014.

[7] O. Whyte, J. Sivic, A. Zisserman, and J. Ponce. “Non-uniform deblurring for shaken images”, IJCV 2012.

[8] A. Gupta, N. Joshi, L. Zitnick, M. Cohen, and B. Curless. “Single image deblurring using motion density functions”, ECCV 2010.

[9] A. Levin, Y. Weiss, F. Durand, and W. T. Freeman, “Understanding and evaluating blind deconvolution algorithms,” CVPR 2009.

[10] R. Kohler, M. Hirsch, B. Mohler and B. Scholkopf. “Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database”, ECCV 2012.

[11] L. Sun, S. Cho, J.Wang, and J. Hays. "Edge-based blur kernel estimation using patch priors", ICCP 2013.