[1] A KARAALI, N HARTE, C R JUNG. Deep multi-scale feature learning for defocus blur estimation. IEEE Transactions on Image Processing, 31, 1097-1106(2022).

[2] H Y MA, S J LIU, Q M LIAO et al. Defocus image deblurring network with defocus map estimation as auxiliary task. IEEE Transactions on Image Processing, 31, 216-226(2022).

[3] [3] 杨昊元. 基于图像统计特征的可见光图像复原方法研究［D］. 北京： 中国科学院大学， 2021.YANGH Y. Visible Image Restoration Methods Based on Image Statistical Features［D］. Beijing： University of Chinese Academy of Sciences， 2021. （in Chinese）

[4] M Q CHEN, Y H QUAN, T Y PANG et al. Nonblind image deconvolution via leveraging model uncertainty in an untrained deep neural network. International Journal of Computer Vision, 130, 1770-1789(2022).

[5] [5] 陈清江， 胡倩楠， 李金阳. 多尺度交替连接残差网络用于图像去模糊［J］. 光学 精密工程， 2021， 29（7）： 1686-1694. doi: 10.37188/OPE.20212907.1686CHENQ J， HUQ N， LIJ Y. Image deblurring based on multi-scale alternating connection residual network［J］. Opt. Precision Eng.， 2021， 29（7）： 1686-1694. （in Chinese）. doi: 10.37188/OPE.20212907.1686

[6] D HUO, A MASOUMZADEH, Y H YANG. Blind non-uniform motion deblurring using atrous spatial pyramid deformable convolution and deblurring-reblurring consistency(2022).

[7] [7] 杨航. 非盲图像复原综述［J］. 中国光学（中英文）， 2022（5）： 954-972. doi: 10.37188/co.2022-0099HANGY. Survey of non-blind image restoration［J］. Chinese Optics， 2022（5）： 954-972.（in Chinese）. doi: 10.37188/co.2022-0099

[8] D ZORAN, Y WEISS. From learning models of natural image patches to whole image restoration, 479-486(6).

[9] K WONG, F LI. Fast Parameter Estimation Using Green’s Functions. Advances in Neural Information Processing Systems 14(2001).

[10] N JOSHI, C LAWRENCE ZITNICK, R SZELISKI et al. Image deblurring and denoising using color priors, 1550-1557(20).

[11] J S PAN, Z HU, Z X SU et al. Deblurring text images via L0-regularized intensity and gradient Prior, 2901-2908(23).

[12] [12] 闫敬文， 彭鸿， 刘蕾， 等. 基于L0正则化模糊核估计的遥感图像复原［J］. 光学 精密工程， 2014， 22（9）： 2572-2579. doi: 10.3788/ope.20142209.2572YANJ W， PENGH， LIUL， et al. Remote sensing image restoration based on zero-norm regularized kernel estimation［J］. Opt. Precision Eng.， 2014， 22（9）： 2572-2579. （in Chinese）. doi: 10.3788/ope.20142209.2572

[13] [13] 曹学影， 王琳， 谭覃燕， 等. 自适应双刃边法模糊红外图像复原［J］. 光学 精密工程， 2022， 30（5）： 630-640. doi: 10.37188/OPE.20223005.0620CAOX Y， WANGL， TANQ Y， et al. Restoration of blurred infrared image by adaptive double edge method［J］. Opt. Precision Eng.， 2022， 30（5）： 630-640. （in Chinese）. doi: 10.37188/OPE.20223005.0620

[14] P TRAN, A T TRAN, Q PHUNG et al. Explore image deblurring via encoded blur kernel space, 11951-11960(20).

[15] T H KIM, K M LEE. Deep multi-scale convolutional neural network for dynamic scene deblurring, 257-265(21).

[16] X TAO, H Y GAO, X Y SHEN et al. Scale-recurrent network for deep image deblurring, 8174-8182(18).

[17] L CHEN, X CHU, X ZHANG et al. Simple Baselines for Image Restoration. arXiv, 2204-04676(2022). https：//arxiv.org/abs/2204.04676

[18] L Y PAN, R HARTLEY, M M LIU et al. Phase-only image based kernel estimation for single image blind deblurring, 6027-6036(15).

[19] A KAUFMAN, R FATTAL. Deblurring using analysis-synthesis networks pair. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 5810-5819(2020).

[20] D W REN, K ZHANG, Q L WANG et al. Neural blind deconvolution using deep priors, 3338-3347(13).

[21] V LEMPITSKY, A VEDALDI, D ULYANOV. Deep image prior, 9446-9454(18).

[22] Z W LUO, H B HUANG, L YU et al. Deep constrained least squares for blind image super-resolution, 17621-17631(18).

[23] J DONG, S ROTH, B SCHIELE. Deep Wiener Deconvolution： Wiener Meets Deep Learning for Image Deblurring. arXiv, 2103-09962(2021). https：//arxiv.org/abs/2103.09962.pdf

[24] E AGUSTSSON, R TIMOFTE. NTIRE 2017 challenge on single image super-resolution： dataset and study, 1122-1131(21).

[25] J J GU, H N LU, W M ZUO et al. Blind super-resolution with iterative kernel correction, 1604-1613(15).

[26] D R I M SETIADI. PSNR vs SSIM： imperceptibility quality assessment for image steganography. Multimedia Tools and Applications, 80, 1-22(2020).

[27] Y WANG. FTVd is Beyond Fast Total Variation Regularized Deconvolution. arXiv, 1402-3869(2014). https：//arxiv.org/abs/1402.3869.pdf