Overview of Image Denoising Methods

doi:10.3778/j.issn.1673-9418.2101035

Abstract

Abstract:

In real scenes, due to the imperfections of equipment and systems or the existence of low-light environments, the collected images are noisy. The images will also be affected by additional noise during the compression and transmission process, which will interfere with subsequent image segmentation and feature extraction processes. Traditional denoising methods use the non-local self-similarity (NLSS) characteristics of the image and the sparse representation in the transform domain, and the method based on block-matching and three-dimensional filtering (BM3D) shows a powerful image denoising performance. With the development of artificial intelligence, image denoising methods based on deep learning have achieved outstanding performance. But so far, there is almost no relevant research on the comprehensive comparison of image denoising methods. Aiming at the traditional image denoising methods and the image denoising methods based on deep neural networks that have emerged in recent years, this paper first introduces the basic framework of the classic traditional denoising and deep neural network denoising methods and classifies and summarizes the denoising methods. Then the existing denoising methods are analyzed and compared quantitatively and qualitatively on the public denoising data set. Finally, this paper points out some potential challenges and future research directions in the field of image denoising.

Key words: non-local similarity, transform domain, block matching technology, deep neural network

摘要：

在现实场景中，由于设备和系统不完善或存在弱光环境导致采集的图像存在噪声，图像在压缩和传输过程中也会受到额外噪声的影响，给后续的图像分割、特征提取等处理造成干扰。传统去噪方法利用图像的非局部自相似性（NLSS）特性和变换域中的稀疏表示，基于块匹配和三维滤波（BM3D）的方法展现出了强大的图像去噪性能。随着人工智能的发展，基于深度学习的图像去噪方法取得了较为突出的表现。但是到目前为止几乎没有相关研究对图像去噪的方法进行全面的比较。针对传统的图像去噪方法及近年来兴起的基于深度神经网络的图像去噪方法，首先介绍了经典的传统去噪和深度神经网络去噪方法的基本框架，并对去噪方法进行了分类总结。然后在公共去噪数据集上对现有的去噪方法进行了定量和定性方面的分析比较。最后在图像去噪领域指出了一些潜在的挑战和未来研究的方向。

关键词: 非局部相似性, 变换域, 块匹配技术, 深度神经网络

LIU Liping, QIAO Lele, JIANG Liucheng. Overview of Image Denoising Methods[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(8): 1418-1431.

刘利平, 乔乐乐, 蒋柳成. 图像去噪方法概述[J]. 计算机科学与探索, 2021, 15(8): 1418-1431.

References

[1] YANG C J. Research on several issues of image denoising and its effect evaluation[D]. Changchun: Jilin University, 2016.
杨成佳. 图像去噪及其效果评估若干问题研究[D]. 长春：吉林大学, 2016.
[2] JIN K H, MCCANN M T, FROUSTEY E, et al. Deep convolutional neural network for inverse problems in imaging[J]. IEEE Transactions on Image Processing, 2017, 26(9): 4509-4522.
[3] FAROOQUE M A, ROHANKAR J S. Survey on various noises and techniques for denoising the color image[J]. International Journal of Application or Innovation in Engineering & Management, 2013, 2(11): 217-221.
[4] WIENER N, WIENER N, MATHEMATICIAN C, et al. Extrapolation, interpolation, and smoothing of stationary time series: with engineering applications[M]. Cambridge: MIT Press, 1949.
[5] DABOV K, FOI A, KATKOVNIK V, et al. Image denoising by sparse 3-D transform-domain collaborative filtering[J]. IEEE Transactions on Image Processing, 2007, 16(8): 2080-2095.
[6] YAROSLAVSKY L P, EGIAZARIAN K O, ASTOLA J T. Transform domain image restoration methods: review, comparison, and interpretation[J]. Proceedings of SPIE-The International Society for Optical Engineering, 2001, 4304: 155-169.
[7] KONG Z, YANG X, HE L. A comprehensive comparison of multi-dimensional image denoising methods[J]. arXiv:2011.03462, 2020.
[8] DABOV K, FOI A, KATKOVNIK V, et al. Color image denoising via sparse 3D collaborative filtering with grouping constraint in luminance-chrominance space[C]//Proceedings of the 2007 International Conference on Image Processing, San Antonio, Sep 16-19, 2007. Piscataway: IEEE, 2007: 313-316.
[9] DANIELYAN A, FOI A, KATKOVNIK V, et al. Denoising of multispectral images via nonlocal groupwise spectrum-PCA[C]//Proceedings of the 5th European Conference on Colour in Graphics, Imaging, and Vision, and the 12th International Symposium on Multispectral Colour Science, Joensuu, Jun 14-17, 2010. Piscataway: IEEE, 2010: 261-266.
[10] MAGGIONI M, KATKOVNIK V, EGIAZARIAN K, et al. Nonlocal transform-domain filter for volumetric data denoising and reconstruction[J]. IEEE Transactions on Image Processing, 2012, 22(1): 119-133.
[11] TANG C, XU J L, ZHOU Z G. Strong noise image-denoising algorithm based on improved curvature filters[J]. Journal of Image and Graphics, 2019, 24(3): 346-356.
汤成, 许建龙, 周志光. 改进的曲率滤波强噪声图像去噪方法[J]. 中国图象图形学报, 2019, 24(3): 346-356.
[12] ZHANG H J, ZHANG D M, YAN W, et al. Wavelet transform image denoising algorithm based on improved threshold function[J]. Application Research of Computers, 2020, 37(5): 1545-1548.
张绘娟, 张达敏, 闫威, 等. 基于改进阈值函数的小波变换图像去噪算法[J]. 计算机应用研究, 2020, 37(5): 1545-1548.
[13] LI G H, LI J J, FAN H. Image denoising algorithm based on adaptive matching pursuit[J]. Computer Science, 2020, 47(1): 176-185.
李桂会, 李晋江, 范辉. 自适应匹配追踪图像去噪算法[J]. 计算机科学, 2020, 47(1): 176-185.
[14] YUAN X J, ZHOU T, LI C. Research on image denoising algorithm based on non-local clustering with sparse prior [J]. Computer Engineering and Applications, 2020, 56(18): 177-185.
袁小军, 周涛, 李琛. 基于稀疏先验的非局域聚类图像去噪算法研究[J]. 计算机工程与应用, 2020, 56(18): 177-185.
[15] BUADES A, COLL B, MOREL J M. A non-local algorithm for image denoising[C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, Jun 20-26, 2005. Washington: IEEE Computer Society, 2005: 60-65.
[16] CHANG Y Y, ZHANG X D. Non-local image denoising algorithm based on multi-scale similarity prior[J]. Computer Knowledge and Technology, 2020, 16(2): 200-203.
常圆圆, 张选德. 基于多尺度相似先验的非局部图像去噪算法[J]. 电脑知识与技术, 2020, 16(2): 200-203.
[17] MO Y G. Research on image denoising method based on structure prior and sparse representation[D]. Xi??an: Xidian University, 2019.
莫一过. 基于结构先验与稀疏表示的图像去噪方法研究[D]. 西安：西安电子科技大学, 2019.
[18] LIU C S, ZHAO Z G, LI Q, et al. Enhanced low-rank representation image denoising algorithm[J]. Computer Engineering and Applications, 2020, 56(2): 216-225.
刘成士, 赵志刚, 李强, 等. 加强的低秩表示图像去噪算法[J]. 计算机工程与应用, 2020, 56(2): 216-225.
[19] LYU J R, LUO X G, QI S F, et al. Image denoising using weighted nuclear norm minimization with preserving local structure[J]. Laser & Optoelectronics Progress, 2019, 56(16): 57-64.
吕俊瑞, 罗学刚, 岐世峰, 等. 保持局部结构的加权核范数最小化图像去噪[J]. 激光与光电子学进展, 2019, 56(16): 57-64.
[20] BUADES A, COLL B, MOREL J M. Non-local means denoising[J]. Image Processing on Line, 2011, 1: 208-212.
[21] KNAUS C, ZWICKER M. Progressive image denoising[J]. IEEE Transactions on Image Processing, 2014, 23(7): 3114-3125.
[22] GONG Y, SBALZARINI I F. Curvature filters efficiently reduce certain variational energies[J]. IEEE Transactions on Image Processing, 2017, 26(4): 1786-1798.
[23] WU G W, WANG C M, BAO J D, et al. A wavelet threshold de-noising algorithm based on adaptive threshold function[J]. Journal of Electronics & Information Technology, 2014, 36(6): 1340-1347.
吴光文, 王昌明, 包建东, 等. 基于自适应阈值函数的小波阈值去噪方法[J]. 电子与信息学报, 2014, 36(6): 1340-1347.
[24] ELAN M, AHARON M. Image denoising via sparse and redundant representations over learned dictionaries[J]. IEEE Transactions on Image Processing, 2006, 15(12): 3736-3745.
[25] DONG W, ZHANG L, SHI G, et al. Nonlocally centralized sparse representation for image restoration[J]. IEEE Transactions on Image Processing, 2012, 22(4): 1620-1630.
[26] XU J, ZHANG L, ZHANG D. A trilateral weighted sparse coding scheme for real-world image denoising[C]//LNCS 11212: Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 21-38.
[27] WEN B, RAVISHANKAR S, BRESLER Y. Structured overcomplete sparsifying transform learning with convergence guarantees and applications[M]. Hingham: Kluwer Academic Publishers, 2015.
[28] MAIRAL J, BACH F, PONCE J, et al. Non-local sparse models for image restoration[C]//Proceedings of the IEEE 12th International Conference on Computer Vision, Kyoto, Sep 27-Oct 4, 2009. Washington: IEEE Computer Society, 2009: 2272-2279.
[29] ZHANG J, ZHAO D, GAO W. Group-based sparse representation for image restoration[J]. IEEE Transactions on Image Processing, 2014, 23(8): 3336.
[30] XU J, ZHANG L, ZHANG D. External prior guided internal prior learning for real-world noisy image denoising[J]. IEEE Transactions on Image Processing, 2018, 27(6): 2996-3010.
[31] HOU Y K, XU J, LIU M X, et al. NLH: a blind pixel-level non-local method for real-world image denoising[J]. IEEE Transactions on Image Processing, 2020, 29: 5121-5135.
[32] ZUO W M, ZHANG L, SONG C W, et al. Texture enhanced image denoising via gradient histogram preservation[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, Jun 23-28, 2013. Washington: IEEE Computer Society, 2013: 1203-1210.
[33] XU J, ZHANG L, ZUO W M, et al. Patch group based nonlocal self-similarity prior learning for image denoising [C]//Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Dec 7-13, 2015. Washington: IEEE Computer Society, 2015: 244-252.
[34] CHEN F, ZHANG L, YU H M. External patch prior guided internal clustering for image denoising[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Dec 7-13, 2015. Washington: IEEE Computer Society, 2015: 603-611.
[35] ZORAN D, WEISS Y. From learning models of natural image patches to whole image restoration[C]//Proceedings of the 2011 IEEE International Conference on Computer Vision, Barcelona, Nov 6-13, 2011. Washington: IEEE Computer Society, 2011: 479-486.
[36] DONG W S, SHI G M, LI X. Nonlocal image restoration with bilateral variance estimation: a low-rank approach[J]. IEEE Transactions on Image Processing, 2013, 22(2): 700-711.
[37] GU S H, ZHANG L, ZUO W M, et al. Weighted nuclear norm minimization with application to image denoising [C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Jun 23-28, 2014. Washington: IEEE Computer Society, 2014: 2862-2869.
[38] XU J, ZHANG L, ZHANG D, et al. Multi-channel weighted nuclear norm minimization for real color image denoising[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 1105-1113.
[39] LIU C S. Research on image denoising algorithm based on low-rank matrix restoration[D]. Chengdu: Southwest Jiaotong University, 2019.
刘成士. 基于低秩矩阵恢复的图像去噪算法的研究[D]. 成都: 西南交通大学, 2019.
[40] CHANG Y, YAN L X, ZHONG S. Hyper-Laplacian regularized unidirectional low-rank tensor recovery for multispectral image denoising[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 5901-5909.
[41] ZHUANG L N, BIOUCAS-DIAS J M. Fast hyperspectral image denoising and inpainting based on low-rank and sparse representations[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(3): 730-742.
[42] ZHANG K, ZUO W M, CHEN Y J, et al. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising [J]. IEEE Transactions on Image Processing, 2017, 26(7): 3142-3155.
[43] VALSESIA D, FRACASTORO G, MAGLI E. Deep graph-convolutional image denoising[J]. IEEE Transactions on Image Processing, 2020, 29: 8226-8237.
[44] YAN H S, CHEN X, TAN V Y F, et al. Unsupervised image noise modeling with self-consistent GAN[J]. arXiv:1906. 05762, 2019.
[45] ZHAO D, MA L, LI S N, et al. End-to-end denoising of dark burst images using recurrent fully convolutional networks[J]. arXiv:1904.07483, 2019.
[46] YANG J Y, LIU X, SONG X L, et al. Estimation of signal-dependent noise level function using multi-column convolutional neural network[C]//Proceedings of the 2017 IEEE International Conference on Image Processing, Beijing, Sep 17-20, 2017. Piscataway: IEEE, 2017: 2418-2422.
[47] YU S, PARK B, JEONG J. Deep iterative down-up CNN for image denoising[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 2095-2103.
[48] CHEN J W, CHEN J W, CHAO H Y, et al. Image blind denoising with generative adversarial network based noise modeling[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 3155-3164.
[49] BURGER H C, SCHULER C J, HARMELING S. Image denoising: can plain neural networks compete with BM3D?[C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, Jun 16-21, 2012. Washington: IEEE Computer Society, 2012: 2392-2399.
[50] ZHANG K, LI Y, ZUO W, et al. Plug-and-play image restoration with deep denoiser prior[J]. arXiv:2008.13751, 2020.
[51] CHEN Y J, POCK T. Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(6): 1256-1272.
[52] TIAN C W, XU Y, FEI L K, et al. Enhanced CNN for image denoising[J]. CAAI Transactions on Intelligence Technology, 2019, 4(1): 17-23.
[53] WANG T Y, SUN M X, HU K N. Dilated deep residual network for image denoising[C]//Proceedings of the 29th IEEE International Conference on Tools with Artificial Intelligence, Boston, Nov 6-8, 2017. Washington: IEEE Computer Society, 2017: 1272-1279.
[54] JIA X X, LIU S Y, FENG X C, et al. FOCNet: a fractional optimal control network for image denoising[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 6054-6063.
[55] CRUZ C, FOI A, KATKOVNIK V, et al. Nonlocality-reinforced convolutional neural networks for image denoising[J]. IEEE Signal Processing Letters, 2018, 25(8): 1216-1220.
[56] WANG X H, LIU F, MA X C. Color image denoising based on depth residual learning[J]. Packaging Engineering, 2019, 40(17): 235-242.
王晓红, 刘芳, 麻祥才. 基于深度残差学习的彩色图像去噪研究[J]. 包装工程, 2019, 40(17): 235-242.
[57] SCHMIDT U, ROTH S. Shrinkage fields for effective image restoration[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Jun 23-28, 2014. Washington: IEEE Computer Society, 2014: 2774-2781.
[58] TAI Y, YANG J, LIU X M, et al. Memnet: a persistent memory network for image restoration[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 4539-4547.
[59] MA H Q, MA S P, XU Y L, et al. Image denoising based on improved stacked sparse denoising autoencoder[J]. Computer Engineering and Applications, 2018, 54(4): 199-204.
马红强, 马时平, 许悦雷, 等. 基于改进栈式稀疏去噪自编码器的图像去噪[J]. 计算机工程与应用, 2018, 54(4): 199-204.
[60] CHEN M Y, LI R X, LIU H, et al. Pre-filtering-based group sparse residual constraint image denoising model [J]. Transducer and Microsystem Technologies, 2020, 39(2): 48-51.
陈梦雅, 李润鑫, 刘辉, 等. 基于预滤波的组稀疏残差约束图像去噪模型[J]. 传感器与微系统, 2020, 39(2): 48-51.
[61] CHANG M, LI Q, FENG H J, et al. Spatial-adaptive network for single image denoising[J]. arXiv:2001.10291, 2020.
[62] ANWAR S, BARNES N. Real image denoising with feature attention[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 3155-3164.
[63] YUE Z S, YONG H W, ZHAO Q, et al. Variational denoising network: toward blind noise modeling and removal[C]//Proceedings of the 32nd Annual Conference on Neural Information Processing Systems, Vancouver, Dec 8-14, 2019. Red Hook: Curran Associates, 2019: 1688-1699.
[64] TIAN C W, XU Y, ZUO W M, et al. Designing and training of a dual CNN for image denoising[J]. arXiv:2007.03951, 2020.
[65] TIAN C W, XU Y, LI Z Y, et al. Attention-guided CNN for image denoising[J]. Neural Networks, 2020, 124: 117-129.
[66] TIAN C W, XU Y, ZUO W M. Image denoising using deep CNN with batch renormalization[J]. Neural Networks, 2020, 121: 461-473.
[67] LIU D, WEN B H, FAN Y C, et al. Non-local recurrent network for image restoration[C]//Proceedings of the 31st Annual Conference on Neural Information Processing Systems, Montréal, Dec 3-8, 2018. Red Hook: Curran Associates, 2018: 1680-1689.
[68] ZHANG K, ZUO W M, GU S H, et al. Learning deep CNN denoiser prior for image restoration[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 2808-2817.
[69] GUO S, YAN Z F, ZHANG K, et al. Toward convolutional blind denoising of real photographs[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 1712-1722.
[70] ZAMIR S W, ARORA A, KHAN S, et al. CycleISP: real image restoration via improved data synthesis[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 2693-2702.
[71] YUE Z S, ZHAO Q, ZHANG L, et al. Dual adversarial network: toward real-world noise removal and noise generation[C]//LNCS 12355: Proceedings of the 16th European Conference on Computer Vision, Glasgow, Aug 23-28, 2020. Cham: Springer, 2020: 41-58.
[72] ZAMIR S W, ARORA A, KHAN S, et al. Learning enriched features for real image restoration and enhancement[J]. arXiv:2003.06792, 2020.
[73] SONG Y D, ZHU Y F, DU X. Grouped multi-scale network for real-world image denoising[J]. IEEE Signal Processing Letters, 2020, 27: 2124-2128.
[74] ZHOU Y Q, JIAO J B, HUANG H B, et al. When AWGN-based denoiser meets real noises[J]. arXiv:1904.03485, 2019.
[75] KAI Z, ZUO W, LEI Z. FFDNet: toward a fast and flexible solution for CNN-based image denoising[J]. IEEE Transactions on Image Processing, 2018, 27(9): 4608-4622.
[76] ISOGAWA K, IDA T, SHIODEERA T, et al. Deep shrinkage convolutional neural network for adaptive noise reduction[J]. IEEE Signal Processing Letters, 2017, 25(2): 224-228.
[77] SOLTANAYEV S, CHUN S Y. Training deep learning based denoisers without ground truth data[C]//Proceedings of the 31st Annual Conference on Neural Information Processing Systems, Montréal, Dec 3-8, 2018. Red Hook: Curran Associates, 2018: 3257-3267.
[78] JASZEWSKI M, PARAMESWARAN S. Exploring efficient and tunable convolutional blind image denoising networks[C]//Proceedings of the 48th IEEE Applied Imagery Pattern Recognition Workshop, Washington, Oct 15-17, 2019. Piscataway: IEEE, 2019: 1-9.
[79] YEH R A, LIM T Y, CHEN C, et al. Image restoration with deep generative models[C]//Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Apr 15-20, 2018. Piscataway: IEEE, 2018: 6772-6776.
[80] LI X M, LIU M, YE Y T, et al. Learning warped guidance for blind face restoration[C]//LNCS 11217: Proceedings of the European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 278-296.
[81] KIM Y, SOH J W, PARK G Y, et al. Transfer learning from synthetic to real-noise denoising with adaptive instance normalization[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 3479-3489.
[82] ZHANG K, ZUO W M, ZHANG L. Learning a single convolutional super-resolution network for multiple degradations[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 3262-3271.
[83] CHIANG Y W, SULLIVAN B J. Multi-frame image restoration using a neural network[C]//Proceedings of the 32nd Midwest Symposium on Circuits and Systems, Champaign, Aug 14-16, 1989. Piscataway: IEEE, 1989: 744-747.
[84] ZHOU Y T, CHELLAPPA R, JENKINS B K. A novel approach to image restoration based on a neural network[C]//Proceedings of the IEEE 1st International Conference on Neural Networks, San Diego, 1987. Piscataway: IEEE, 1987: 269-276.
[85] TIAN C W, FEI L K, ZHENG W X, et al. Deep learning on image denoising: an overview[J]. arXiv:1912.13171, 2019.
[86] LIU D, WEN B H, JIAO J B, et al. Connecting image denoising and high-level vision tasks via deep learning[J]. IEEE Transactions on Image Processing, 2020, 29: 3695-3706.
[87] WU Q B, REN W Q, CAO X C. Learning interleaved cascade of shrinkage fields for joint image dehazing and denoising[J]. IEEE Transactions on Image Processing, 2020, 29: 1788-1801.
[88] LIU L, JIA X, LIU J Z, et al. Joint demosaicing and denoising with self guidance[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 2237-2246.
[89] QIAN G C, GU J J, REN J S, et al. Trinity of pixel enhancement: a joint solution for demosaicking, denoising and super- resolution[J]. arXiv:1905.02538, 2019.