Blind Image Deblurring via Deep Discriminative Priors

Abstract

We present an effective blind image deblurring method based on a data-driven discriminative prior. Our work is motivated by the fact that a good image prior should favor sharp images over blurred ones. In this work, we formulate the image prior as a binary classifier using a deep convolutional neural network. The learned prior is able to distinguish whether an input image is sharp or not. Embedded into the maximum a posterior framework, it helps blind deblurring in various scenarios, including natural, face, text, and low-illumination images, as well as non-uniform deblurring. However, it is difficult to optimize the deblurring method with the learned image prior as it involves a non-linear neural network. In this work, we develop an efficient numerical approach based on the half-quadratic splitting method and gradient descent algorithm to optimize the proposed model. Furthermore, we extend the proposed model to handle image dehazing. Both qualitative and quantitative experimental results show that our method performs favorably against the state-of-the-art algorithms as well as domain-specific image deblurring approaches.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24

References

  1. Berman, D., Treibitz, T., & Avidan, S. (2016). Non-local image dehazing. In IEEE conference on computer vision and pattern recognition.

  2. Bigdeli, S. A., Zwicker, M., Favaro, P., & Jin, M. (2017). Deep mean-shift priors for image restoration. In Neural information processing systems.

  3. Boracchi, G., & Foi, A. (2012). Modeling the performance of image restoration from motion blur. IEEE Transactions on Image Processing, 21(8), 3502–3517.

    MathSciNet  Article  MATH  Google Scholar 

  4. Chakrabarti, A. (2016). A neural approach to blind motion deblurring. In European conference on computer vision.

  5. Cho, S., & Lee, S. (2009). Fast motion deblurring. ACM Transactions on Graphics, 28(5), 145.

    Article  Google Scholar 

  6. Dong, C., Loy, C. C., He, K., & Tang, X. (2014). Learning a deep convolutional network for image super-resolution. In European conference on computer vision.

  7. Dong, C., Deng, Y., Change Loy, C., & Tang, X. (2015). Compression artifacts reduction by a deep convolutional network. In IEEE international conference on computer vision.

  8. Fergus, R., Singh, B., Hertzmann, A., Roweis, S. T., & Freeman, W. T. (2006). Removing camera shake from a single photograph. ACM Transactions on Graphics, 25(3), 787–794.

    Article  MATH  Google Scholar 

  9. Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics (pp. 249–256).

  10. He, K., Sun, J., & Tang, X. (2011). Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12), 2341–2353.

    Article  Google Scholar 

  11. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In IEEE Conference on computer vision and pattern recognition.

  12. Hirsch, M., Schuler, C. J., Harmeling, S., & Schölkopf, B. (2011). Fast removal of non-uniform camera shake. In IEEE International conference on computer vision.

  13. Hradiš, M., Kotera, J., Zemcík, P., & Šroubek, F. (2015). Convolutional neural networks for direct text deblurring. In British machine vision conference.

  14. Hu, Z., & Yang, M. H. (2012). Good regions to deblur. In European conference on computer vision.

  15. Hu, Z., Cho, S., Wang, J., & Yang, M. H. (2014). Deblurring low-light images with light streaks. In IEEE conference on computer vision and pattern recognition.

  16. Huiskes, M. J., & Lew, M. S. (2008). The MIR flickr retrieval evaluation. In ACM international conference on multimedia information retrieval.

  17. Jin, M., Hirsch, M., & Favaro, P. (2018). Learning face deblurring fast and wide. In IEEE conference on computer vision and pattern recognition workshops.

  18. Kim, J., Lee, J. K., & Lee, K. M. (2016). Accurate image super-resolution using very deep convolutional networks. In IEEE conference on computer vision and pattern recognition.

  19. 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 European conference on computer vision.

  20. Krishnan, D., & Fergus, R. (2009). Fast image deconvolution using hyper-laplacian priors. In Neural information processing systems.

  21. Krishnan, D., Tay, T., & Fergus, R. (2011). Blind deconvolution using a normalized sparsity measure. In IEEE conference on computer vision and pattern recognition.

  22. Kupyn, O., Budzan, V., Mykhailych, M., Mishkin, D., & Matas, J. (2018). Deblurgan: Blind motion deblurring using conditional adversarial networks. In IEEE conference on computer vision and pattern recognition.

  23. Lai, W. S., Ding, J. J., Lin, Y. Y., & Chuang, Y. Y. (2015). Blur kernel estimation using normalized color-line prior. In IEEE conference on computer vision and pattern recognition.

  24. Lai, W. S., Huang, J. B., Ahuja, N., & Yang, M. H. (2017). Deep laplacian pyramid networks for fast and accurate super-resolution. In IEEE conference on computer vision and pattern recognition.

  25. Lai, W. S., Huang, J. B., Hu, Z., Ahuja, N., & Yang, M. H. (2016). A comparative study for single image blind deblurring. In IEEE conference on computer vision and pattern recognition.

  26. Leclaire, A., & Moisan, L. (2013). Blind deblurring using a simplified sharpness index. In International conference on scale space and variational methods in computer vision.

  27. Levin, A., Weiss, Y., Durand, F., & Freeman, W. T. (2009). Understanding and evaluating blind deconvolution algorithms. In IEEE conference on computer vision and pattern recognition.

  28. Levin, A., Weiss, Y., Durand, F., & Freeman, W. T. (2011). Efficient marginal likelihood optimization in blind deconvolution. In IEEE conference on computer vision and pattern recognition.

  29. Li, B., Peng, X., Wang, Z., Xu, J., & Feng, D. (2017a). Aod-net: All-in-one dehazing network. In IEEE international conference on computer vision.

  30. Li, B., Peng, X., Wang, Z., Xu, J. Z., & Feng, D. (2017b). Aod-net: All-in-one dehazing network. In IEEE international conference on computer vision.

  31. Li, B., Ren, W., Fu, D., Tao, D., Feng, D., Zeng, W., et al. (2019). Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing, 28(1), 492–505.

    MathSciNet  Article  MATH  Google Scholar 

  32. Lin, M., Chen, Q., & Yan, S. (2013). Network in network. arXiv:1312.4400.

  33. Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In IEEE conference on computer vision and pattern recognition.

  34. Mao, X., Shen, C., & Yang, Y. B. (2016). Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In Neural information processing systems.

  35. Michaeli, T., & Irani, M. (2014). Blind deblurring using internal patch recurrence. In European conference on computer vision.

  36. Nah, S., Kim, T. H., & Lee, K. M. (2017). Deep multi-scale convolutional neural network for dynamic scene deblurring. In IEEE conference on computer vision and pattern recognition. https://doi.org/10.1109/CVPR.2017.35.

  37. Noroozi, M., Chandramouli, P., & Favaro, P. (2017). Motion deblurring in the wild. In German conference on pattern recognition.

  38. Pan, J., Hu, Z., Su, Z., Yang, M. H. (2014a). Deblurring face images with exemplars. In European conference on computer vision.

  39. Pan, J., Hu, Z., Su, Z., Yang, M. H. (2014b). Deblurring text images via l0-regularized intensity and gradient prior. In IEEE conference on computer vision and pattern recognition.

  40. Pan, J., Sun, D., Pfister, H., & Yang, M. H. (2016). Blind image deblurring using dark channel prior. In IEEE conference on computer vision and pattern recognition.

  41. Pan, J., Sun, D., Pfister, H., & Yang, M.-H. (2018). Deblurring images via dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(10), 2315–2328.

    Article  Google Scholar 

  42. Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., & Yang, M. H. (2016). Single image dehazing via multi-scale convolutional neural networks. In European conference on computer vision.

  43. Schuler, C. J., Hirsch, M., Harmeling, S., & Schölkopf, B. (2016). Learning to deblur. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(7), 1439–1451.

    Article  Google Scholar 

  44. Shen, Z., Lai, W. S., Xu, T., Kautz, J., & Yang, M. H. (2018). Deep semantic face deblurring. In IEEE conference on computer vision and pattern recognition.

  45. Sreehari, S., Venkatakrishnan, S. V., Wohlberg, B., Buzzard, G. T., Drummy, L. F., Simmons, J. P., et al. (2016). Plug-and-play priors for bright field electron tomography and sparse interpolation. IEEE Transactions on Computational Imaging, 2(4), 408–423.

    MathSciNet  Google Scholar 

  46. Sun, J., Cao, W., Xu, Z., & Ponce, J. (2015). Learning a convolutional neural network for non-uniform motion blur removal. In IEEE conference on computer vision and pattern recognition.

  47. Sun, L., Cho, S., Wang, J., & Hays, J. (2013). Edge-based blur kernel estimation using patch priors. In IEEE international conference on computational photography.

  48. Tai, Y. W., Tan, P., & Brown, M. S. (2011). Richardson-lucy deblurring for scenes under a projective motion path. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(8), 1603–1618.

    Article  Google Scholar 

  49. Tao, X., Gao, H., Shen, X., Wang, J., & Jia, J. (2018). Scale-recurrent network for deep image deblurring. In IEEE conference on computer vision and pattern recognition.

  50. Vedaldi, A., & Lenc, K. (2015). Matconvnet: Convolutional neural networks for matlab. In ACM international conference on multimedia.

  51. Whyte, O., Sivic, J., Zisserman, A., & Ponce, J. (2012). Non-uniform deblurring for shaken images. International Journal of Computer Vision, 98(2), 168–186.

    MathSciNet  Article  MATH  Google Scholar 

  52. Xu, L., & Jia, J. (2010). Two-phase kernel estimation for robust motion deblurring. In European conference on computer vision.

  53. Xu, L., Lu, C., Xu, Y., & Jia, J. (2011). Image smoothing via \(l_0\) gradient minimization. ACM Transactions on Graphics, 30(6), 174.

    Google Scholar 

  54. Xu, L., Zheng, S., & Jia, J. (2013). Unnatural l0 sparse representation for natural image deblurring. In IEEE conference on computer vision and pattern recognition.

  55. Yan, R., & Shao, L. (2016). Blind image blur estimation via deep learning. IEEE Transactions on Image Processing, 25(4), 1910–1921.

    MathSciNet  MATH  Google Scholar 

  56. Yan, Y., Ren, W., Guo, Y., Wang, R., & Cao, X. (2017). Image deblurring via extreme channels prior. In IEEE conference on computer vision and pattern recognition.

  57. Zhang, J., Pan, J., Lai, W. S., Lau, R., & Yang, M. H. (2017a). Learning fully convolutional networks for iterative non-blind deconvolution. In IEEE conference on computer vision and pattern recognition.

  58. Zhang, K., Zuo, W., Gu, S., & Zhang, L. (2017b). Learning deep CNN denoiser prior for image restoration. In IEEE conference on computer vision and pattern recognition.

  59. Zhao, P., Cheng, Y., & Pedersen, M. (2015). Objective assessment of perceived sharpness of projection displays with a calibrated camera. In Colour and visual computing symposium.

  60. Zoran, D., & Weiss, Y. (2011). From learning models of natural image patches to whole image restoration. In IEEE international conference on computer vision.

Download references

Acknowledgements

This work is partially supported by the National Natural Science Foundation of China (Nos. 61433007 and 61872421), the National Science Foundation CAREER (No. 1149783), the Natural Science Foundation of Jiangsu Province (No. BK20180471), and gifts from Adobe and Nvidia. Lerenhan Li is supported by a scholarship from China Scholarship Council.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Nong Sang.

Additional information

Publisher's Note

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

Communicated by Svetlana Lazebnik.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Li, L., Pan, J., Lai, W. et al. Blind Image Deblurring via Deep Discriminative Priors. Int J Comput Vis 127, 1025–1043 (2019). https://doi.org/10.1007/s11263-018-01146-0

Download citation

Keywords

  • Blind mage deblurring
  • Deep learning
  • Discriminative prior