Abstract
Deblurring images with outliers has always been a significantly challenging problem. Previous methods mainly involved complex operations, such as outlier and light streak detection, or sophisticated image priors for blur-kernel estimation, which increased the difficulty of deblurring images. Therefore, we developed a simple, yet efficient, blind deblurring algorithm in this study for handling images with outliers. To eliminate the impact of outliers during the kernel estimation process, we employed a robust Welsch loss function to characterize the data-fidelity term of our model. We observed that this function could extract significant edges successfully. Therefore, the image regularization term was also described by the same function. Using this unified robust function to describe our model can considerably reduce the complexity of the algorithm. Moreover, we derived a flexible weight function from the Welsch function to further improve the efficiency of our algorithm. To finally obtain accurate latent images, we developed a robust non-blind deblurring approach based on this flexible weight function. The experimental results indicate that our approach outperforms state-of-the-art methods in deblurring images with or without outliers. Compared with the method specifically for outliers, the recovery performance of our method can be improved by 12.9% (considering a dataset with impulse noise), and the execution efficiency is about 1.5 times faster.
Similar content being viewed by others
Data Availability
The data that support the findings of this study are available from the corresponding author on request.
References
H. Badri, H. Yahia, D. Aboutajdine, Fast edge-aware processing via first order proximal approximation. IEEE Trans. Visual Comput. Graph. 21(6), 743–755 (2015)
J. T. Barron, A general and adaptive robust loss function, in: CVPR, 2019, pp. 4331–4339
A. Chakrabarti, A neural approach to blind motion deblurring, in: ECCV, 2016, pp. 221–235
L. Chen, F. Fang, T. Wang, G. Zhang, Blind image deblurring with local maximum gradient prior, in: CVPR, 2019, pp. 1743–1750
S. Cho, S. Lee, Fast motion deblurring. ACM Trans. Graph. 28(5), 1–8 (2009)
S. Cho, J. Wang, S. Lee, Handling outliers in non-blind image deconvolution, in: ICCV, 2011, pp. 495–502
J.E. Dennis Jr., R.E. Welsch, Techniques for nonlinear least squares and robust regression. Commun. Stat.-Simul. Comput. 7(4), 345–359 (1978)
J. Dong, J. Pan, Z. Su, M.-H. Yang, Blind image deblurring with outlier handling, in: ICCV, 2017, pp. 2478–2486
J. Dong, J. Pan, D. Sun, Z. Su, M.-H. Yang, Learning data terms for non-blind deblurring, in: ECCV, 2018, pp. 777–792
R. Fergus, B. Singh, A. Hertzmann, S.T. Roweis, W.T. Freeman, Removing camera shake from a single photograph. ACM Trans. Graph. 25(3), 787–794 (2006)
D. Gong, M. Tan, Y. Zhang, A. Hengel, Q. Shi, Blind image deconvolution by automatic gradient activation, in: CVPR, 2016, pp. 1827–1836
D. Gong, M. Tan, Y. Zhang, A. Hengel, Q. Shi, Self-paced kernel estimation for robust blind image deblurring, in: ICCV, 2017, pp. 1661–1670
B. Ham, M. Cho, J. Ponce, Robust guided image filtering using nonconvex potentials. IEEE Trans. Pattern Anal. Mach. Intell. 40(1), 192–207 (2018)
M. Hirsch, C.J. Schuler, S. Harmeling, B. Schölkopf, Fast removal of non-uniform camera shake, in: ICCV, 2011, pp. 463–470
Z. Hu, S. Cho, J. Wang, M.-H. Yang, Deblurring low-light images with light streaks, in: CVPR, 2014, pp. 3382–3389
N. Joshi, R. Szeliski, D.J. Kriegman, PSF estimation using sharp edge prediction, in: CVPR, 2008, pp. 1–8
R. Köhler, M. Hirsch, B. Mohler, B. Schölkopf, S. Harmeling, Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database, in: ECCV, 2012, pp. 27–40
D. Krishnan, J. Bruna, R. Fergus, Blind deconvolution with re-weighted sparsity promotion, 2013. CoRR abs/1311.4029
D. Krishnan, R. Fergus, Fast image deconvolution using Hyper-Laplacian priors, in: NIPS, 2009, pp. 1033–1041
D. Krishnan, T. Tay, R. Fergus, Blind deconvolution using a normalized sparsity measure, in: CVPR, 2011, pp. 233–240
O. Kupyn, V. Budzan, M. Mykhailych, D. Mishkin, J. Matas, DeblurGAN: blind motion deblurring using conditional adversarial networks, in: CVPR, 2017, pp.8183–8192
A. Levin, R. Fergus, F. Durand, W.T. Freeman, Image and depth from a conventional camera with a coded aperture. ACM Trans. Graph. 26(3), 70–78 (2007)
A. Levin, Y. Weiss, F. Durand, W.T. Freeman, Understanding and evaluating blind deconvolution algorithms, in: CVPR, 2009, pp. 1964–1971
A. Levin, Y. Weiss, F. Durand, W.T. Freeman, Efficient marginal likelihood optimization in blind deconvolution, in: CVPR, 2011, pp. 2657–2664
L. Li, J. Pan, W.-S. Lai, C. Gao, N. Sang, M.-H. Yang, Blind image deblurring via deep discriminative priors. Int. J. Comput. Vis. 127(8), 1025–1043 (2019)
J. Liu, M. Yan, T. Zeng, Surface-aware blind image deblurring. IEEE Trans. Pattern Anal. Mach. Intell. (2019). https://doi.org/10.1109/TPAMI.2019.2941472
T. Michaeli, M. Irani, Blind deblurring using internal patch recurrence, in: ECCV, 2014, pp. 783–798
S.Nah, T. Kim, K. Lee, Deep multi-scale convolutional neural network for dynamic scene deblurring, in: CVPR, 2017, pp. 3883–3891
J. Pan, Z. Hu, Z. Su, M.-H. Yang, Deblurring text images via L0-regularized intensity and gradient prior, in: CVPR, 2014, pp. 2901–2908
J. Pan, Z. Lin, Z. Su, M.-H. Yang, Robust kernel estimation with outliers handling for image deblurring, in: CVPR, 2016, pp. 2800–2808
J. Pan, R. Liu, Z. Su, X. Gu, Kernel estimation from salient structure for robust motion deblurring. Signal Process.: Image Commun. 28(9), 1156–1170 (2013)
J. Pan, Z. Su, Fast L0-regularized kernel estimation for robust motion deblurring. IEEE Signal Process. Lett. 20(9), 841–844 (2013)
J. Pan, D. Sun, H. Pfister, M.-H. Yang, Blind image deblurring using dark channel prior, in: CVPR, 2016, pp. 1628–1636
D. Perrone, R. Diethelm, P. Favaro, Blind deconvolution via lower-bounded logarithmic image priors, in: EMMCVPR, 2015, pp. 112–125
D. Perrone, P. Favaro, Total variation blind deconvolution: the devil is in the details, in: CVPR, 2014, pp. 2909–2916
W. Ren, X. Cao, J. Pan, X. Guo, W. Zuo, M.-H. Yang, Image deblurring via enhanced low rank prior. IEEE Trans. Image Process. 25(7), 3426–3437 (2016)
Q. Shan, J. Jia, A. Agarwala, High-quality motion deblurring from a single image. ACM Trans. Graph. 27(3), 1–10 (2008)
J. Sun, W. Cao, Z. Xu, J. Ponce, Learning a convolutional neural network for non-uniform motion blur removal, in: CVPR, 2015, pp.769–777
L. Sun, S. Cho, J. Wang, J. Hays, Edge-based blur kernel estimation using patch priors, in: ICCP, 2013, pp. 1–8
Y. Tang, Y. Xue, Y. Chen, L. Zhou, Blind deblurring with sparse representation via external patch priors. Digital Signal Process. 78, 322–331 (2018)
X. Tao, H. Gao, X. Shen, J. Wang, J. Jia, Scale-recurrent network for deep image deblurring, in: CVPR, 2018, pp. 8174–8182
O. Whyte, J. Sivic, A. Zisserman, Deblurring shaken and partially saturated images. Int. J. Comput. Vis. 110(2), 185–201 (2014)
L. Xu, J. Jia, Two-phase kernel estimation for robust motion deblurring, in: ECCV, 2010, pp. 157–170.
L. Xu, J. Ren, C. Liu, J. Jia, Deep convolutional neural network for image deconvolution, in: NIPS, 2014, pp. 1790–1798
L. Xu, S. Zheng, J. Jia, Unnatural L0 sparse representation for natural image deblurring, in: CVPR, 2013, pp. 1107–1114
Z. Xu, H. Chen, Z. Li, Blind image deblurring using group sparse representation. Digital Signal Process. (2020). https://doi.org/10.1016/j.dsp.2020.102736
Z. Xu, H. Chen, Z. Li, Blind image deblurring via the weighted Schatten p-norm minimization prior. Circuits Syst. Signal Process. 39, 6191–6230 (2020)
Z. Xu, H. Chen, Z. Li, Fast blind deconvolution using a deeper sparse patch-wise maximum gradient prior. Signal Process.: Image Commun. (2020). https://doi.org/10.1016/j.image.2020.116050
Y. Yan, W. Ren, Y. Guo, R. Wang, X. Cao, Image deblurring via extreme channels prior, in: CVPR, 2017, pp. 6978–6986
J. Zhang, J. Pan, J. Ren, Y. Song, L. Bao, R. Lau, M.-H. Yang, Dynamic scene deblurring using spatially variant recurrent neural networks, in: CVPR, 2018, pp. 2521–2529
X. Zhou, M. Vega, F. Zhou, R. Molina, A.K. Katsaggelos, Fast Bayesian blind deconvolution with Huber Super Gaussian priors. Digital Signal Process. 60, 122–133 (2017)
D. Zoran, Y. Weiss, From learning models of natural image patches to whole image restoration, in: ICCV, 2011, pp. 479–486
Acknowledgements
This work has been supported by National Natural Science Foundation of China (Grant No. 61971225), and National Science and Industry Bureau (Grant No. JCKY2016606B001). We would like to thank Editage (www.editage.cn) for English language editing.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflicts of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xu, Z., Lai, J., Zhou, J. et al. Image Deblurring Using a Robust Loss Function. Circuits Syst Signal Process 41, 1704–1734 (2022). https://doi.org/10.1007/s00034-021-01857-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-021-01857-9