Abstract
Non-blind image deblurring has attracted a lot of attention in the field of low-level vision. However, the existing non-blind deblurring methods cannot effectively deal with a saturated blurry image. The key point is that the degradation model of saturated blurry images does not satisfy the linear convolution model of a conventional blurry image. To solve the problem, in this paper, we proposed a novel deep non-blind deblurring method, dubbed saturated image non-blind deblurring network(SDBNet). The SDBNet contains two trainable sub-network, i.e., confident estimate network (CEN) and detail enhance network (DEN). Specifically, the SDBNet uses CEN to estimate the confidence map for the saturated blurry image, which is used to recognize saturated pixels in the blurry image, and then uses the confidence map, and blur kernel to restore the blurry image. Finally, we use DEN to enhance the edges and textures of the restored image. We first pre-train CEN and DEN. In order to effectively pre-train CEN, we propose a new robust function, which is used to generate label data for CEN. The experimental results show that compared with several existing non-blind deblurring methods, SDBNet can effectively restore saturated blurry images and better restore the texture, edge, and other structural information of blurry images.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Code availability
Not applicable.
References
Cheng S, Liu R, He Y, Fan X, Luo Z (2020) Blind image deblurring via hybrid deep priors modeling. Neurocomputing 387:334–345
Javaran TA, Hassanpour H, Abolghasemi V (2017) Non-blind image deconvolution using a regularization based on re-blurring process. Comput Vis Image Underst 154:16–34
Wang W, Su C (2022) An optimization method for motion blur image restoration and ringing suppression via texture mapping. ISA Trans 131:650–661
Richardson WH (1972) Bayesian-based iterative method of image restoration. JOSA 62(1):55–59
Wiener N, Wiener N, Mathematician C, Wiener N, Wiener N, Mathématicien C (1949) Extrapolation, interpolation, and smoothing of stationary time series: with engineering applications, vol. 113, no. 21
Krishnan D, Fergus R (2009) Fast image deconvolution using hyper-laplacian priors. In: NeurIPS, pp 1033–1041
Chan SH, Wang X, Elgendy OA (2017) Plug-and-play ADMM for image restoration: fixed-point convergence and applications. IEEE Trans Comput 3(1):84–98
Schmidt U, Rother C, Nowozin S, Jancsary J, Roth S (2013) Discriminative non-blind deblurring. In: IEEE CVPR, pp 604–611
Schmidt U, Jancsary J, Nowozin S, Roth S, Rother C (2016) Cascades of regression tree fields for image restoration. IEEE Trans Pattern Anal Mach Intell 38(4):677–689
Tappen MF, Liu C, Adelson EH, Freeman WT (2007) Learning gaussian conditional random fields for low-level vision. In: IEEE CVPR
Zoran D, Weiss Y (2011) From learning models of natural image patches to whole image restoration. In: IEEE ICCV, pp 479–486
Chen Y, Yu W, Pock T (2015) On learning optimized reaction diffusion processes for effective image restoration. In: IEEE CVPR, pp 5261–5269
Chen Y, Pock T (2017) Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration. IEEE Trans Pattern Anal Mach Intell 39(6):1256–1272
Zhang K, Zuo W, Gu S, Zhang L (2017) Learning deep CNN denoiser prior for image restoration. In: IEEE CVPR, pp 3929–3938
Zhang K, Li Y, Zuo W, Zhang L, Van Gool L, Timofte R (2021) Plug-and-play image restoration with deep denoiser prior. IEEE Trans Pattern Anal Mach Intell 44(10):6360–6376
Zhang J, Pan J, Lai W-S, Lau RW, Yang MH (2017) Learning fully convolutional networks for iterative non-blind deconvolution. In: IEEE CVPR, pp 3817–3825
Chen L, Zhang J, Lin S, Fang F, Ren JS (2021) Blind deblurring for saturated images. In: IEEE CVPR, pp 6308–6316
Cho S, Wang J, Lee S (2011) Handling outliers in non-blind image deconvolution. In: IEEE ICCV, pp 495–502
Whyte O, Sivic J, Zisserman A (2014) Deblurring shaken and partially saturated images. Int J Comput Vision 110(2):185–201
Pan J, Lin Z, Su Z, Yang M (2016) Robust kernel estimation with outliers handling for image deblurring. In: IEEE CVPR, pp 2800–2808
Zhang X, Wang R, Chen D, Zhao Y, Gao W (2021) Handling outliers by robust m-estimation in blind image deblurring. IEEE Trans Multimed 23:3215–3226
Dong J, Pan J (2021) Deep outlier handling for image deblurring. IEEE Trans Image Process 30:1799–1811
Chen L, Zhang J, Pan J, Lin S, Fang F, Ren JS (2021) Learning a non-blind deblurring network for night blurry images. In: IEEE CVPR, Vol. 10, pp 542–550
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
Chen L, Fang F, Wang T, Zhang G (2019) Blind image deblurring with local maximum gradient prior. In: IEEE CVPR, pp 1742–1750
Shan Q, Jia J, Agarwala A (2008) High-quality motion deblurring from a single image. ACM Trans Graph 27(3):73
Pan J, Hu Z, Su Z, Yang M (2014) Deblurring text images via l0-regularized intensity and gradient prior. In: IEEE CVPR, pp 2901–2908
Pan J, Hu Z, Su Z, Yang M-H (2016) \(l_0\)-regularized intensity and gradient prior for deblurring text images and beyond. IEEE Trans Pattern Anal Mach Intell 39(2):342–355
Xu L, Zheng S, Jia J (2013) Unnatural L0 sparse representation for natural image deblurring. In: IEEE CVPR, pp 1107–1114
Ren W, Cao X, Pan J, Guo X, Zuo W, Yang M (2016) Image deblurring via enhanced low-rank prior. IEEE Trans Image Process 25(7):3426–3437
Yan Y, Ren W, Guo Y, Wang R, Cao X (2017) Image deblurring via extreme channels prior. In: IEEE CVPR, pp 6978–6986
Rudin LI, Osher SJ (1994) Total variation based image restoration with free local constraints. In: IEEE ICIP, pp 31–35
Wang Y, Yang J, Yin W, Zhang Y (2008) A new alternating minimization algorithm for total variation image reconstruction. SIAM J Imag Sci 1(3):248–272
Fortunato HE, Oliveira MM (2014) Fast high-quality non-blind deconvolution using sparse adaptive priors. Visual Comput 30(6–8):661–671
Schmidt U, Gao Q, Roth S (2010) A generative perspective on MRFS in low-level vision. In: IEEE CVPR, pp. 1751–1758
Schmidt U, Roth S (2014) Shrinkage fields for effective image restoration. In: IEEE CVPR, pp 2774–2781
Li L, Pan J, Lai W, Gao C, Sang N, Yang M (2019) Blind image deblurring via deep discriminative priors. Int J Comput Vision 127(8):1025–1043
Zhang J, Pan J, Lai W, Lau RWH, Yang M (2017) Learning fully convolutional networks for iterative non-blind deconvolution. In: IEEE CVPR, pp 6969–6977
Gong D, Zhang Z, Shi Q, van den Hengel A, Shen C, Zhang Y (2020) Learning deep gradient descent optimization for image deconvolution. IEEE Trans Neural Netw Learn Syst 31(12):5468–5482
Dong J, Roth S, Schiele B (2021) Learning spatially-variant MAP models for non-blind image deblurring. In: IEEE CVPR, pp 4886–4895
Wang D, Tang H, Pan J, Tang J (2021) Learning a tree-structured channel-wise refinement network for efficient image deraining. In: IEEE ICME, pp 1–6
Wang D, Pan J, Tang J (2023) Single image deraining using residual channel attention networks. J Comput Sci Technol 38(2):439–454
Dong J, Pan J, Su Z, Yang M (2017) Blind image deblurring with outlier handling. In: IEEE ICCV, pp 2497–2505
Hu Z, Cho S, Wang J, Yang M (2014) Deblurring low-light images with light streaks. In: IEEE CVPR, pp 3382–3389
Wang D, Liu J, Liu R, Fan X (2023) An interactively reinforced paradigm for joint infrared-visible image fusion and saliency object detection. Inf Fus 98:101828
Zhang Y, Li K, Li K, Wang L, Zhong B, Fu Y (2018) Image super-resolution using very deep residual channel attention networks. In: ECCV, vol. 11211, pp 294–310
Levin A, Weiss Y, Durand F, Freeman W (2009) Understanding and evaluating blind deconvolution algorithms. In: IEEE CVPR, pp 1964–1971
Dabov K, Foi A, Katkovnik V, Egiazarian KO (2008) Image restoration by sparse 3d transform-domain collaborative filtering. In: SPIE, vol. 6812, pp 681207
Schuler CJ, Burger HC, Harmeling S, Schölkopf B (2013) A machine learning approach for non-blind image deconvolution. In: IEEE CVPR, pp 1067–1074
Son H, Lee S (2017) Fast non-blind deconvolution via regularized residual networks with long/short skip-connections. In: IEEE ICCP, pp 23–32
Liu Y, Lai W, Chen Y, Kao Y, Yang M, Chuang Y, Huang J (2020) Single-image HDR reconstruction by learning to reverse the camera pipeline. In: IEEE CVPR, pp 1648–1657
Gharbi M, Chen J, Barron JT, Hasinoff SW, Durand F (2017) Deep bilateral learning for real-time image enhancement. ACM Trans Graph 36(4): 1–12
Ma L, Ma T, Liu R, Fan X, Luo Z (2022) Toward fast, flexible, and robust low-light image enhancement. In: IEEE CVPR, pp 5627–5636
Mildenhall B, Srinivasan PP, Tancik M, Barron JT, Ramamoorthi R, Ng R (2020) Nerf: representing scenes as neural radiance fields for view synthesis. In: Springer ECCV, vol. 12346, pp 405–421
Zheng H, Yong H, Zhang L (2021) Deep convolutional dictionary learning for image denoising. In: IEEE CVPR, pp 630–641
Zhang K, Gool LV, Timofte R (2020) Deep unfolding network for image super-resolution. In: IEEE CVPR, pp 3214–3223
Acknowledgements
This work is supported by the General project of Liaoning Provincial Department of Education, China, No. LJKZ0986; Postdoctoral Science Foundation, No. 2019M651123; Science and Technology Innovation Fund (Youth Science and Technology Star) of Dalian, China, No. 2018RQ65. Fund receiver: Dr. Bo Fu. This work is supported by the National Natural Science Foundation of China (NSFC) Grant No.61976109, China; Liaoning Provincial Key Laboratory Special Fund; Dalian Key Laboratory Special Fund. Fund receiver: Dr. Yonggong Ren. This research was funded by the University of Economics Ho Chi Minh City, Vietnam. Fund receiver: Dr. Dang Ngoc Hoang Thanh.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Fu, B., Fu, S., Wu, Y. et al. Deep non-blind deblurring network for saturated blurry images. Neural Comput & Applic 36, 7829–7843 (2024). https://doi.org/10.1007/s00521-024-09495-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-024-09495-3