Abstract
Blind image deblurring is the process of recovering the original image from a degraded image under unknown point spread function, and it is the solution to an ill-posed inverse problem. In this paper, the blurry image is firstly divided into skeleton image and blur kernel, aiming to achieve accurate blur kernel estimation. Then the advantages of model-based optimization method and discriminative learning method are integrated through variable splitting technique. Finally, a trained convolutional neural network (CNN) is used as a module to be inserted into a model-based optimization method to solve the problem of blind image deblurring more effectively. By comparing visual and quantitative experimental data, the network proposed in this paper can provide powerful prior information for blind image deblurring and the restoration effects can approximate or exceed those of some representative algorithms.
Similar content being viewed by others
Explore related subjects
Find the latest articles, discoveries, and news in related topics.References
Bai Y, Cheung G, Liu X et al (2018) Graph-based blind image Deblurring from a single photograph[J]. IEEE Trans Image Process 28(3):1404–1418
Boyd S, Parikh N, Chu E et al (2010) Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers[J]. Found Trends® Mach Learn 3(1):1–122
Brifman A, Romano Y, Elad M (2016) Turning a denoiser into a super-resolver using plug and play priors[C]// 2016 IEEE International Conference on Image Processing (ICIP). IEEE
Cai JF, Ji H, Liu C, Shen Z (2012) Framelet-based blind motion Deblurring from a single image. IEEE Trans Image Process 21(2):562–572
Chambolle A, De Vore RA, Lee N-Y et al (1998) Nonlinear wavelet image processing: Variational problems, compression, and noise removal through wavelet shrinkage. IEEE Trans Image Process 7(3):319–335
Chan TF, Wong CK (1998) Total variation blind deconvolution. IEEE Trans Image Process 7(3):370–375
Chan SH, Wang X, Elgendy OA (2016) Plug-and-play ADMM for image restoration: fixed point convergence and applications[J]. IEEE Trans Comput Imaging 3(1):84–98
Chen Y, Pock T (2017) Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration[J]. IEEE Trans Patt Analysis Mach Intell 39(6):1256–1272
Cho S, Lee S (2009) Fast motion deblurring. ACM Trans Graph 28(5):1–8
Deng J, Dong W, Socher R, Li L-J, Li K, FeiFei L (2009) Imagenet: a large-scale hierarchical image database. In IEEE Conference on Computer Vision and Pattern Recognition, p. 248–255
Fang H, Yan L, Liu H, Chang Y (2013) Blind Poissonian images deconvolution with framelet regularization. Opt Lett 38(4):389–391
Fereus R, Sineh B, Hertzmann A, Roweis ST, Freeman WT (2006) Removine camera shake from a single photograph. ACM Trans Graph 25(3):787–794
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
Figueiredo MAT, Nowak RD (2003) An EM algorithm for wavelet-based image restoration. IEEE Trans Image Process 12(8):906–916
Gao H, Tao X, Shen X, Jia J (2019) Dynamic Scene Deblurring With Parameter Selective Sharing and Nested Skip Connections. 3843–3851. https://doi.org/10.1109/CVPR.2019.00397
Geman D, Yang C (1994) Nonlinear image recovery with half-quadratic regularization[J]. IEEE Trans Image Process 4(7):932
Gonzalez RC, Woods RE (2007) Digital Image Processing (3rd Edition) [M]. Prentice-Hall, Inc
Hirsch M, Schuler CJ, Harmeling S, Schölkopf B (2011) Fast removal of non-uniform camera shake. 2011 International Conference on Computer Vision, p 463–470
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift[C]// International Conference on International Conference on Machine Learning. JMLR.org
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization[J]. Comp Sci
Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks[C]// NIPS. Curran Associates Inc
Kundur D, Hatzinakos D (1996) Blind image deconvolution. IEEE Signal Process Mag 13(3):43–64
Kundur D, Hatzinakos D (2013) Blind image deconvolution[J]. Signal Process Mag IEEE 13(3):43–64
Kupyn O, Budzan V, Mykhailych M et al (2018) DeblurGAN: blind motion Deblurring using conditional adversarial networks[C]// 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR). IEEE 8183–8192
Kupyn O, Martyniuk T, Wu J, Wang Z (2019) DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 8877–8886
Levin A, Weiss Y, Durand F, Freeman WT (2011) Understanding blind Deconvolution algorithms. IEEE Trans Patt Analysis Mach Intell 33(12):2354–2367
Levin A, Weiss Y, Durand F, Freeman WT (2011) Effificient marginal likelihood optimization in blind deconvolution. In CVPR 2011, p 2657–2664
Li L, Pan J, Lai WS, Gao C, Sang N, Yang MH (2019) Blind image Deblurring via deep discriminative priors[J]. Int J Comput Vis 127:1025–1043
Lu B, Chen J-C, Chellappa R (2019) Unsupervised domain-specific deblurring via disentangled representations. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 10217–10226
Lu X, Wang W, Ma C et al (2019) See more, know more: unsupervised video object segmentation with co-attention Siamese networks[C]// CVPR19. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 3618–3627
Lu X, Wang W, Shen J, Tai Y-W, Crandall D, Hoi S (2020) Learning video object segmentation from unlabeled videos. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 8957–8967
Ma K, Duanmu Z, Wu Q, Wang Z, Yong H, Li H, Zhang L (2017) Waterloo exploration database: new challenges for image quality assessment models. IEEE Trans Image Process 26(2):1004–1016
Malczewski K, Stasinski R (2008) Toeplitz-based iterative image fusion scheme for MRI[C]// IEEE International Conference on Image Processing. IEEE
Pan Z, Yu J et al (2013) Super-resolution based on compressive sensing and structural self-similarity for remote sensing images[J]. IEEE Trans Geoence Remote Sens 51(9):4864–4876
Pan J, Sun D, Pfister H et al. (2016) Blind image Deblurring using Dark Channel prior// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE
Parikh N, Boyd SP (2014) Proximal algorithms. Found Trends R Optim 1:123–231
Romano Y, Elad M, Milanfar P (2016) The little engine that could regularization by denoising (RED). arXiv preprint arXiv:1611.02862
Rond A, Giryes R, Elad M (2016) Poisson inverse problems by the plug-and-play scheme. J Vis Commun Image Represent 41:96–108
Schuler CJ, Hirsch M, Harmeling S et al (2014) Learning to Deblur[J]. IEEE Trans Patt Analysis Mach Intell 38(7):1439–1451
Shan Q, Jia J, Agarwala A (2008) High-quality motion deblurring from a single image. ACM Trans Graph 27(3)73
Shen Z, Wang W, Lu X et al (2019) Human-aware motion Deblurring. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 5571–5580
Sreehari S, Venkatakrishnan SV, Wohlberg B et al (2017) Plug-and-play priors for bright field Electron tomography and sparse interpolation[J]. IEEE Trans Comput Imaging 2(4):408–423
Tao X, Gao H, Wang Y et al. (2018) Scale-recurrent network for deep image Deblurring[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE
Teodoro AM, Bioucas-Dias JM, Figueiredo MA (2016) Image restoration and reconstruction using variable splitting and class-adapted image priors. 2016 IEEE International Conference on Image Processing (ICIP), 3518–3522
Vedaldi A, Lenc K (2015) MatConvNet: convolutional neural networks for matlab. In ACM Conference on Multimedia Conference, p 689–692
Whyte O, Sivic J, Zisserman A, Ponce J (2010) Non-uniform deblurring for shaken images. Int J Comput Vis 98:168–186
Xu L, Jia J (2010) Two-phase kernel estimation for robust motion deblurring[C]// Computer Vision - ECCV 2010, 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I. DBLP
Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions[J]
Zhang J, Pan J, Lai WS et al. (2017) Learning fully convolutional networks for iterative non-blind Deconvolution[J]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6969–6977
Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a Gaussian Denoiser: residual learning of deep CNN for image Denoising. IEEE Trans Image Process 26:3142–3155
Zhang K, Zuo W, Zhang L (2018) Learning a single convolutional super-resolution network for multiple degradations. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 3262–3271
Zhang Y, Li K, Li K, Wang L, Zhong B, Fu Y (2018) Image super-resolution using very deep Residual Channel attention networks. ArXiv, abs/1807.02758
Zhou S, Zhang J, Zuo W, Xie H, Pan J, Ren J (2019) DAVANet: stereo deblurring with view aggregation. 2019 IEEE/CVF Conference on Computer Vision and PatternRecognition (CVPR), 10988–10997
Acknowledgements
We thank Southwest Jiaotong University Photoelectric Engineering Institute for their support in this experiment. This work was supported by grants from National Natural Science Foundation of China (Grant No. 61471304).
Author information
Authors and Affiliations
Corresponding author
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
Bao, J., Luo, L., Zhang, Y. et al. Half quadratic splitting method combined with convolution neural network for blind image deblurring. Multimed Tools Appl 80, 3489–3504 (2021). https://doi.org/10.1007/s11042-020-09821-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09821-6