图像去模糊算法研究综述

doi:10.11896/jsjkx.241200045

摘要/Abstract

摘要： 图像去模糊是计算机视觉中的经典问题,旨在从模糊的输入图像或视频中恢复出清晰的视觉信息。模糊现象通常由相机对焦不准、相机抖动或目标快速运动等因素导致。传统去模糊方法通常将该任务建模为反卷积问题,视模糊图像为清晰图像与模糊核的卷积结果,但在处理复杂或非理想的模糊类型时存在局限性。近年来,基于深度学习的回归方法取得了突破。这类方法借助卷积神经网络(CNN)和Transformer等架构,通过学习模糊与清晰图像间的映射关系,实现了对复杂模糊情况的有效处理,且无需对模糊核进行显式建模。同时,生成式深度学习方法如生成对抗网络(GAN)和扩散模型在去模糊领域逐渐展示出显著潜力。生成式AI通过构建并学习图像的细节生成过程,不仅能够有效去除模糊,还可以生成具有细腻纹理的高质量图像,在复杂模糊场景中表现出优越性能。文中首先介绍了图像模糊的特性,阐述了去模糊的常见任务类别及评估指标,然后深入探讨了去模糊模型的基本架构与训练方法,并比较分析了代表性的前沿图像去模糊模型,最后进一步探讨了图像去模糊在未来可能的研究方向。

关键词: 图像去模糊, 深度学习, 反卷积, 自回归模型, 生成式人工智能

Abstract: Image deblurring is a classic problem in computer vision,aiming to recover sharp visual information from blurry input images or videos.Blur is often caused by factors such as camera misfocus,camera shake,or fast-moving objects.Traditional deblurring methods typically model the task as a deconvolution problem,treating the blurry image as the convolution of a sharp image and a blur kernel.However,these methods face limitations when dealing with complex or non-ideal blur types.In recent years,deep learning-based regression methods have made significant breakthroughs.These approaches leverage architectures such as Convolutional Neural Networks(CNNs) and Transformers to learn the mapping between blurry and sharp images,enabling effective handling of complex blur scenarios without explicit modeling of the blur kernel.Additionally,generative deep learning methods,such as Generative Adversarial Networks(GANs) and Diffusion models,have shown considerable potential in the deblurring field.Generative AI,by modeling and learning the image detail generation process,not only effectively removes blur but also generates high-quality images with fine textures,demonstrating superior performance in challenging blur scenarios.This paper first introduces the characteristics of image blur and outlines common deblurring tasks and evaluation metrics.It then delves into the fundamental architectures and training methods of deblurring models,providing a comparative analysis of representative state-of-the-art deblurring models.Finally,the paper explores potential future research directions in the field of image deblurring.

Key words: Image deblurring, Deep learning, Deconvolution, Autoregression model, Generative artificial intelligence

中图分类号:

TP391.41

陈康, 林建涵, 刘元杰. 图像去模糊算法研究综述[J]. 计算机科学, 2025, 52(11): 98-112. https://doi.org/10.11896/jsjkx.241200045

CHEN Kang, LIN Jianhan, LIU Yuanjie. Survey on Image Deblurring Algorithms[J]. Computer Science, 2025, 52(11): 98-112. https://doi.org/10.11896/jsjkx.241200045

参考文献

[1]ZUO H,FU C,LI S,et al.Adversarial Blur-Deblur Network for Robust UAV Tracking[J].IEEE Robotics and Automation Letters,2023,8(2):1101-1108.
[2]SHORTEN C,KHOSHGOFTAAR T M.A survey on image data augmentation for deep learning[J/OL].https://doi.org/10.1186/s40537-019-0197-0.
[3]SINGH D,SAHU M R.A survey on various image deblurring techniques[J].International Journal of Advanced Research in Computer and Communication Engineering,2013,116:15-18.
[4]CHEN X,HE X,YANG J,et al.An effective document image deblurring algorithm[C]//IEEE Conference on Computer Vision and Pattern Recognition.2011.
[5]USHA RANI B,ARUNA R,VELRAJKUMAR P,et al.Image Denoising Using Deblur Generative Adversarial Network Denoising U-Net[J／OL].Journal of Circuits,Systems and Computers,2024:2550069.https://doi.org/10.1142/5s0218126625500690.
[6]REN S,HE K,GIRSHICK R,et al.Faster r-cnn:Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems.2015.
[7]HE K,GKIOXARI G,DOLLÁR P,et al.Mask r-cnn[C]//IEEE International Conference on Computer Vision.2017.
[8]WANG J,XIANG L Y,HUANG Y B,et al.Prior-guided blind restoration algorithm for iris image[J].Computer Science,2023,50(12):148-155.
[9]HUANG Y Q,ZHENG P Y,JIANG M R,et al.Reconstruction of solar spot diagrams using gated fusion network and residual Fourier transform[J].Computer Science,2023,50(S2):278-284.
[10]WANG J M,LI X F,YE L,et al.Medical image deblurring basedon channel attention structure generative adversarial network[J].Computer Science,2021,48(S1):101-106.
[11]PAN J S.Research progress on image deblurring methods based on deep learning[J].Computer Science,2021,48(3):9-13.
[12]CHO S,LEE S.Fast motion deblurring[C]//ACM SIGGRAPH Asia.2009.
[13]ABUOLAIM A,BROWN M S.Defocus deblurring using dual-pixel data[C]//European Conference on Computer Vision.2020.
[14]HUMMEL R A,KIMIA B,ZUCKER S W.Deblurring gaussianblur[J].Computer Vision,Graphics,and Image Processing,1987,38(1):66-80.
[15]BIGDELI S A,ZWICKER M,FAVARO P,et al.Deep mean-shift priors for image restoration[C]//Advances in Neural Information Processing Systems.2017:763-772.
[16]MATHIEU M,COUPRIE C,LECUN Y.Deep multi-scale video prediction beyond mean square error[J].arXiv:1511.05440,2015.
[17]MOORTHY A K,BOVIK A C.A two-step framework for constructing blind image quality indices[J].IEEE Signal Processing Letters,2010,17(5):513-516.
[18]BABACAN S D,MOLINA R,DO M N,et al.Bayesian blind deconvolution with general sparse image priors[C]//European Conference on Computer Vision.2012.
[19]CHO S,WANG J,LEE S.Handling outliers in non-blind image deconvolution[C]//IEEE International Conference on Computer Vision.2011.
[20]REN W,ZHANG J,MA L,et al.Deep non-blind deconvolution via generalized low-rank approximation[C]//Proceedings of the 32^nd International Conference on Neural Information Processing Systems.2018.
[21]SCHMIDT U,ROTHER C,NOWOZIN S,et al.Discriminative non-blind deblurring[C]//IEEE Conference on Computer Vision and Pattern Recognition.2013.
[22]SCHULER C J,CHRISTOPHER BURGER H,HARMELING S,et al.A machine learning approach for non-blind image deconvolution[C]//IEEE Conference on Computer Vision and Pattern Recognition.2013:1067-1074.
[23]VASU S,REDDY MALIGIREDDY V,RAJAGOPALAN A.Non-blind Deblurring:Handling Kernel Uncertainty with CNNs[C]//IEEE Conference on Computer Vision and Pattern Recognition.2018.
[24]ZHANG J,PAN J,LAI W S,et al.Learning fully convolutional networks for iterative non-blind deconvolution[C]//IEEE Conference on Computer Vision and Pattern Recognition.2017.
[25]WIESCHOLLEK P,HIRSCH M,SCHOLKOPF B,et al.Lear-ning blind motion deblurring[C]//IEEE International Conference on Computer Vision.2017.
[26]SAAD M A,BOVIK A C,CHARRIER C.Blind image quality assessment:A natural scene statistics approach in the DCT domain[J].IEEE Transactions on Image Processing,2012,21(8):3339-3352.
[27]PAN J,SUN D,PFISTER H,et al.Blind image deblurring using dark channel prior[C]//IEEE Conference on Computer Vision and Pattern Recognition.2016.
[28]PAN J,DONG J,TAI Y W,et al.Learning discriminative data fitting functions for blind image deblurring[C]//IEEE International Conference on Computer Vision.2017.
[29]NIMISHA T M,KUMAR SINGH A,RAJAGOPALAN A N.Blur-invariant deep learning for blind-deblurring[C]//IEEE International Conference on Computer Vision.2017.
[30]NAN Y,QUAN Y,JI H.Variational-EM-based Deep Learning for Noise-blind Image Deblurring[C]//IEEE Conference on Computer Vision and Pattern Recognition.2020.
[31]MOORTHY A K,BOVIK A C.Blind image quality assessment:From natural scene statistics to perceptual quality[J].IEEE Transactions on Image Processing,2011,20(12):3350-3364.
[32]MICHAELI T,IRANI M.Blind deblurring using internal patch recurrence[C]//European Conference on Computer Vision.2014.
[33]LI Y,TOFIGHI M,GENG J,et al.Deep algorithm unrolling for blind image deblurring[J].arXiv:1902.03493,2019.
[34]LI L,PAN J,LAI W S,et al.Learning a discriminative prior for blind image deblurring[C]//IEEE Conference on Computer Vision and Pattern Recognition.2018.
[35]LEVIN A,WEISS Y,DURAND F,et al.Understanding andevaluating blind deconvolution algorithms[C]//IEEE Confe-rence on Computer Vision and Pattern Recognition.2009.
[36]LEVIN A.Blind motion deblurring using image statistics[C]//Advances in Neural Information Processing Systems.2007:841-848.
[37]LAI W S,HUANG J B,HU Z,et al.A comparative study for single image blind deblurring[C]//IEEE Conference on Computer Vision and Pattern Recognition.2016.
[38]KUPYN O,BUDZAN V,MYKHAILYCH M,et al.Deblurgan:Blind motion deblurring using conditional adversarial networks[C]//IEEE Conference on Computer Vision and Pattern Recognition.2018.
[39]KRISHNAN D,TAY T,FERGUS R.Blind deconvolution using a normalized sparsity measure[C]//IEEE Conference on Computer Vision and Pattern Recognition.2011.
[40]KÖHLER R,HIRSCH M,MOHLER B,et al.Recording andplayback of camera shake:Benchmarking blind deconvolution with a real-world database[C]//European Conference on Computer Vision.2012.
[41]FIORI S,UNCINI A,PIAZZA F.Blind deconvolution by modified Bussgang algorithm[C]//The IEEE International Sympo-sium on Circuits and Systems.1999:1-4.
[42]CHAN T F,WONG C K.Total variation blind deconvolution[J].IEEE Transactions on Image Processing,1998,7(3):370-375.
[43]CHAKRABARTI A.A neural approach to blind motion deblurring[C]//European Conference on Computer Vision.2016.
[44]AL-AMEEN Z,SULONG G.Deblurring computed tomography medical images using a novel amended landweber algorithm[J].Interdisciplinary Sciences:Computational Life Sciences,2015,7(3):319-325.
[45]ESLAMI S A,HEESS N,WEBER T,et al.Attend,infer,re-peat:Fast scene understanding with generative models[C]//Advances in Neural Information Processing Systems.2016.
[46]LECUN Y,BOSER B,DENKER J S,et al.Backpropagation applied to handwritten zip code recognition[J].Neural computation,1989,1(4):541-551.
[47]MARTIN D,FOWLKES C,TAL D,et al.A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]//IEEE International Conference on Computer Vision.2001.
[48]ZHAO W,ZHENG B,LIN Q,et al.Enhancing diversity of defocus blur detectors via cross-ensemble network[C]//IEEE Conference on Computer Vision and Pattern Recognition.2019.
[49]DU H,LI Z,NIYATO D,et al.Enabling AI-Generated Content Services in Wireless Edge Networks[J].IEEE Wireless Communications,2024,31(3):226-234.
[50]SHAO L,CHEN B,ZHANG Z,et al.Artificial intelligence generated content(AIGC) in medicine:A narrative review[J].Mathematical Biosciences and Engineering,2024,21(1):1672-1711.
[51]LEI Y,LI J,LI Z,et al.Prompt learning in computer vision:a survey[J].Frontiers of Information Technology & Electronic Engineering,2024,25(1):42-63.
[52]WU T,CHEN Z,HE D,et al.CDDM:Channel Denoising Diffusion Models for Wireless Semantic Communications[J].IEEE Transactions on Wireless Communications,2024,23(9):11168-11183.
[53]DENTON E L,CHINTALA S,FERGUS R,et al.Deep generative image models using a Laplacian pyramid of adversarial networks[C]//Advances in Neural Information Processing Systems.2015.
[54]GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets[C]//Advances in Neural Information Processing Systems.2014.
[55]HO J,ERMON S.Generative adversarial imitation learning[C]//Advances in Neural Information Processing Systems.2016.
[56]LEDIG C,THEIS L,HUSZÁR F,et al.Photo-realistic singleimage super-resolution using a generative adversarial network[C]//IEEE Conference on Computer Vision and Pattern Recognition.2017.
[57]PAN J,LIU Y,DONG J,et al.Physics-based generative adversarial models for image restoration and beyond[J].arXiv:1808.00605,2018.
[58]RADFORD A,METZ L,CHINTALA S.Unsupervised representation learning with deep convolutional generative adversarial networks[J].arXiv:1511.06434,2015.
[59]REED S,AKATA Z,YAN X,et al.Generative adversarial text to image synthesis[J].arXiv:1605.05396,2016.
[60]BORACCHI G,FOI A.Modeling the performance of image restoration from motion blur[J].IEEE Transactions on Image Processing,2012,21(8):3502-3517.
[61]SUN J,CAO W,XU Z,et al.Learning a convolutional neuralnetwork for non-uniform motion blur removal[C]//IEEE Conference on Computer Vision and Pattern Recognition.2015.
[62]XU L,JIA J.Two-phase kernel estimation for robust motion deblurring[C]//European Conference on Computer Vision.2010.
[63]XU X,PAN J,ZHANG Y J,et al.Motion blur kernel estimation via deep learning[J].IEEE Transactions on Image Processing,2017,27(1):194-205.
[64]ZHAO H X,CHAO M L,NI F C.Overdrive LUT optimization for LCD by box motion blur measurement and gamma-based thresholding method[C]//SID Symposium Digest of Technical Papers.2008:117-120.
[65]GONG D,ZHANG Z,SHI Q,et al.Learning Deep Gradient Descent Optimization for Image Deconvolution[J].IEEE Transactions on Neural Networks and Learning Systems,2020,31(12):5468-5482.
[66]GOLDSTEIN A,FATTAL R.Blur-kernel estimation from spectral irregularities[C]//European Conference on Computer Vision.2012.
[67]SON C H,PARK H M.A pair of noisy/blurry patches-based PSF estimation and channel-dependent deblurring[J].IEEE Transactions on Image Processing,2011,57(4):1791-1799.
[68]SUN L,CHO S,WANG J,et al.Edge-based blur kernel estimation using patch priors[C]//IEEE International Conference on Computational Photography.2013.
[69]ALJADAANY R,PAL D K,SAVVIDES M.Douglas-rachfordnetworks:Learning both the image prior and data fidelity terms for blind image deconvolution[C]//IEEE Conference on Computer Vision and Pattern Recognition.2019.
[70]ZHANG K,ZUO W,GU S,et al.Learning deep CNN denoiser prior for image restoration[C]//IEEE Conference on Computer Vision and Pattern Recognition.2017.
[71]CHEN F,MA J.An empirical identification method of Gaussian blur parameter for image deblurring[J].IEEE Transactions on Signal Processing,2009,57(7):2467-2478.
[72]GETREUER P.A survey of Gaussian convolution algorithms[J].Image Processing on Line,2013,2013:286-310.
[73]VAIRY M,VENKATESH Y V.Deblurring Gaussian blur using a wavelet array transform[J].Pattern Recognition,1995,28(7):965-976.
[74]SUN D,YANG X,LIU M Y,et al.PWC-Net:Cnns for optical flow using pyramid,warping,and cost volume[C]//IEEE Conference on Computer Vision and Pattern Recognition.2018.
[75]HOSSFELD T,HEEGAARD P E,VARELA M,et al.QoE be-yond the MOS:an in-depth look at QoE via better metrics and their relation to MOS[J].Quality and User Experience,2016,1(1):2.
[76]HORE A,ZIOU D.Image quality metrics:PSNR vs.SSIM[C]//IEEE International Conference on Pattern Recognition.2010.
[77]WANG Z,BOVIK A C,SHEIKH H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transactions on Image Processing,2004,13(4):600-612.
[78]MITSA T,VARKUR K L.Evaluation of contrast sensitivityfunctions for the formulation of quality measures incorporated in halftoning algorithms[C]//IEEE International Conference on Acoustics,Speech,and Signal Processing.1993.
[79]WANG Z,SIMONCELLI E P,BOVIK A C.Multiscale structural similarity for image quality assessment[C]//The Asilomar Conference on Signals,Systems,and Computers.2003.
[80]SHEIKH H R,BOVIK A C,DE VECIANA G.An information fidelity criterion for image quality assessment using natural scene statistics[J].IEEE Transactions on Image Processing,2005,14(12):2117-2128.
[81]DAMERA-VENKATA N,KITE T D,GEISLER W S,et al.Image quality assessment based on a degradation model[J].IEEE Transactions on Image Processing,2000,9(4):636-650.
[82]WANG Z,BOVIK A C.A universal image quality index[J].IEEE signal processing letters,2002,9(3):81-84.
[83]WUN L M,PEARN W L.Assessing the statistical characteristics of the mean absolute error or forecasting[J].International Journal of Forecasting,1991,7(3):335-337.
[84]SHEIKH H R,BOVIK A C.Image information and visual quali-ty[J].IEEE Transactions on Image Processing,2006,15(2):430-444.
[85]ZHANG R,ISOLA P,EFROS A A,et al.The Unreasonable Effectiveness of Deep Features as a Perceptual Metric[C]//IEEE Conference on Computer Vision and Pattern Recognition.2018.
[86]SHARVIT Y.The puzzle of free indirect discourse[J].Linguistics and Philosophy,2008,31(3):353-395.
[87]BEIER F,BEINERT R,STEIDL G.On a Linear Gromov-Wasserstein Distance[J].IEEE Transactions on Image Processing,2022,31:7292-7305.
[88]MITTAL A,MOORTHY A K,BOVIK A C.No-reference image quality assessment in the spatial domain[J].IEEE Transactions on Image Processing,2012,21(12):4695-4708.
[89]YE P,KUMAR J,KANG L,et al.Unsupervised feature learning framework for no-reference image quality assessment[C]//IEEE Conference on Computer Vision and Pattern Recognition.2012.
[90]MITTAL A,SOUNDARARAJAN R,BOVIK A C.Making a“completely blind” image quality analyzer[J].IEEE Signal Processing Letters,2012,20(3):209-212.
[91]LIU L,LIU B,HUANG H,et al.No-reference image quality assessment based on spatial and spectral entropies[J].Signal Processing:Image Communication,2014,29(8):856-863.
[92]TANG C,WANG P,ZHANG C,et al.Salient object detection via weighted low rank matrix recovery[J].IEEE Signal Processing Letters,2016,24(4):490-494.
[93]JIANG P,LING H,YU J,et al.Salient region detection by ufo:Uniqueness,focusness and objectness[C]//IEEE International Conference on Computer Vision.2013.
[94]FERGUS R,SINGH B,HERTZMANN A,et al.Removing cam-era shake from a single photograph[C]//ACM SIGGRAPH.2006.
[95]XU L,ZHENG S,JIA J.Unnatural l0 sparse representation for natural image deblurring[C]//IEEE Conference on Computer Vision and Pattern Recognition.2013.
[96]PAN J,HU Z,SU Z,et al.Deblurring text images via L0-regularized intensity and gradient prior[C]//IEEE Conference on Computer Vision and Pattern Recognition.2014.
[97]HRADIŠ M,KOTERA J,ZEMCIK P,et al.Convolutional neural networks for direct text deblurring[C]//British Machine Vision Conference.2015.
[98]KALIFA J,MALLAT S,ROUGE B.Deconvolution by thresholding in mirror wavelet bases[J].IEEE Transactions on Image Processing,2003,12(4):446-457.
[99]CHEN F,HUANG X,CHEN W.Texture-Preserving Image Deblurring[J].IEEE Signal Processing Letters,2010,17(12):1018-1021.
[100]DANIELYAN A,KATKOVNIK V,EGIAZARIAN K.BM3Dframes and variational image deblurring[J].IEEE Transactions on Image Processing,2011,21(4):1715-1728.
[101]YUAN L,SUN J,QUAN L,et al.Progressive inter-scale and intra-scale non-blind image deconvolution[J].ACM Transactions on Graphics,2008,27(3):1-10.
[102]KRISHNAN D,FERGUS R.Dark flash photography[J].ACM Transactions on Graphics,2009,28(3):1-11.
[103]ZORAN D,WEISS Y.From learning models of natural image patches to whole image restoration[C]//IEEE International Conference on Computer Vision.2011.
[104]KHERADMAND A,MILANFAR P.A general framework for regularized,similarity-based image restoration[J].IEEE Transactions on Image Processing,2014,23(12):5136-5151.
[105]LANZA A,MORIGI S,SGALLARI F.Convex Image Denoising via Non-convex Regularization with Parameter Selection[J].Journal of Mathematical Imaging and Vision,2016,56(2):195-220.
[106]KHETKEEREE S,LIANGROCAPART S.Image RestorationUsing Optimized Weiner Filtering Based on Modified Tikhonov Regularization[C]//2019 IEEE 4th International Conference on Signal and Image Processing(ICSIP).Wuxi,China:IEEE,2019:1015-1020.
[107]SHAN Q,XIONG W,JIA J.Rotational motion deblurring of a rigid object from a single image[C]//IEEE International Conference on Computer Vision.2007.
[108]XU Y,LI Q Y.Blind deblurring of binary images based onsparse characteristics[J].Computer Science,2018,45(3):255-259.
[109]LEVIN A,WEISS Y,DURAND F,et al.Efficient marginal likelihood optimization in blind deconvolution[C]//CVPR 2011.2011:2657-2664.
[110]YAN Y,REN W,GUO Y,et al.Image Deblurring via Extreme Channels Prior[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Honolulu,HI:IEEE,2017:6978-6986.
[111]YANG L,JI H.A Variational EM Framework With Adaptive Edge Selection for Blind Motion Deblurring[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Long Beach,CA,USA:IEEE,2019:10159-10168.
[112]KRISHNAN D,FERGUS R.Fast image deconvolution usinghyper-Laplacian priors[C]//Advances in Neural Information Processing Systems.2009.
[113]CHEN L,FANG F,WANG T,et al.Blind Image DeblurringWith Local Maximum Gradient Prior[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Long Beach,CA,USA:IEEE,2019:1742-1750.
[114]ZHAO Z G,CHEN Y Y,ZHAO Y,et al.Motion deblurring based on edge prior model[J].Computer Science,2015,42(5):305-308.
[115]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.2016.
[116]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[J].arXiv:1706.03762,2017.
[117]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//The International Conference on Medical Image Computing and Computer-assisted Intervention.2015.
[118]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv:1409.1556,2014.
[119]CIPOLLA R,GAL Y,KENDALL A.Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA:IEEE,2018:7482-7491.
[120]GIRARDIN V.Entropy Maximization for Markov and Semi-Markov Processes[J].Methodology and Computing in Applied Probability,2004,6(1):109-127.
[121]KUPYN O,MARTYNIUK T,WU J,et al.Deblurgan-v2:Deblurring(orders-of-magnitude) faster and better[C]//IEEE International Conference on Computer Vision.2019.
[122]PUROHIT K,RAJAGOPALAN A.Region-Adaptive DenseNetwork for Efficient Motion Deblurring[J].arXiv:1903.11394,2019.
[123]ZHANG K,LUO W,ZHONG Y,et al.Deblurring by realistic blurring[C]//IEEE Conference on Computer Vision and Pattern Recognition.2020.
[124]TAO X,GAO H,SHEN X,et al.Scale-recurrent network fordeep image deblurring[C]//IEEE Conference on Computer Vision and Pattern Recognition.2018.
[125]GAO H,TAO X,SHEN X,et al.Dynamic scene deblurring with parameter selective sharing and nested skip connections[C]//IEEE Conference on Computer Vision and Pattern Recognition.2019.
[126]ZHAO Q,ZHOU D M,YANG H,et al.Image deblurring via residual attention and multi-feature fusion[J].Computer Science,2023,50(1):147-155.
[127]SHEN Z,WANG W,LU X,et al.Human-Aware Motion De-blurring[C]//IEEE International Conference on Computer Vision.2019.
[128]CHILD R,GRAY S,RADFORD A,et al.Generating Long Sequences with Sparse Transformers[J].arXiv:1904.10509,2019.
[129]BELTAGY I,PETERS M E,COHAN A.Longformer:TheLong-Document Transformer[J].arXiv:2004.05150,2020.
[130]ZAHEER M,GURUGANESH G,DUBEY K A,et al.Big Bird:Transformers for Longer Sequences[C]//NeurIPS.2020:17283-17297.
[131]TAY Y,BAHRI D,YANG L,et al.Sparse Sinkhorn Attention[C]//ICML.2020:9438-9447.
[132]KITAEV N,KAISER L,LEVSKAYA A.Reformer:The Efficient Transformer[C]//ICLR.2020.
[133]WANG S,LI B Z,KHABSA M,et al.Linformer:Self-Attention with Linear Complexity[J].arXiv:2004.04768,2020.
[134]TAY Y,BAHRI D,METZLER D,et al.Synthesizer:Rethinking Self-Attention in Transformer Models[J/OL].https://proceedings.mlr.press/v139/tay21a/tay21a.pdf.
[135]KATHAROPOULOS A,VYAS A,PAPPAS N,et al.Trans-formers are RNNs:Fast Autoregressive Transformers with Linear Attention[C]//ICML.2020:5156-5165.
[136]CHOROMANSKI K,LIKHOSHERSTOV V,DOHAN D,et al.Rethinking Attention with Performers[J].arXiv:2009.14794,2020.
[137]DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An Image is Worth 16x16 Words:Transformers for Image Recognition at Scale[J].arXiv:2010.11929,2020.
[138]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-basedlearning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[139]LIU Z,LIN Y,CAO Y,et al.Swin Transformer:Hierarchical Vision Transformer using Shifted Windows[J].arXiv:2103.14030,2021.
[140]HASSANI A,WALTON S,LI J,et al.Neighborhood Attention Transformer[J].arXiv:2204.07143,2022.
[141]BURGER H C,SCHULER C J,HARMELING S.Image denoising:Can plain neural networks compete with BM3D?[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition.Providence,RI:IEEE,2012:2392-2399.
[142]DAUPHIN Y N,FAN A,AULI M,et al.Language Modelingwith Gated Convolutional Networks[J].arXiv:1612.08083,2016.
[143]LIU H,DAI Z,SO D R,et al.Pay Attention to MLPs[J].arXiv:2105.08050,2021.
[144]LI J,HASSANI A,WALTON S,et al.ConvMLP:Hierarchical Convolutional MLPs for Vision[J].arXiv:2109.04454,2021.
[145]CHEN L,CHU X,ZHANG X,et al.Simple Baselines for Image Restoration[J].arXiv:2204.04676,2022.
[146]TAY Y,DEHGHANI M,ABNAR S,et al.Long Range Arena:A Benchmark for Efficient Transformers[C]//ICLR.2021.
[147]SUN L,HAYS J.Super-resolution from internet-scale scenematching[C]//IEEE International Conference on Computational Photography.2012.
[148]NAH S,HYUN KIM T,MU LEE K.Deep multi-scale convolutional neural network for dynamic scene deblurring[C]//IEEE Conference on Computer Vision and Pattern Recognition.2017.
[149]JIANG Z,ZHANG Y,ZOU D,et al.Learning Event-Based Motion Deblurring[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Seattle,WA,USA:IEEE,2020:3317-3326.
[150]SCHARSTEIN D,BRIGGS A J.Real-time recognition of self-similar landmarks[J].Image and Vision Computing,2001,19(11):763-772.
[151]MA L,LI X,LIAO J,et al.Deblur-NeRF:Neural RadianceFields from Blurry Images[J].arXiv:2111.14292,2021.
[152]SHI J P,XU L,JIA J Y.Discriminative Blur Detection Features[C]//IEEE Conference on Computer Vision and Pattern Recognition.2014.
[153]RIM J,LEE H,WON J,et al.Real-world blur dataset for learning and benchmarking deblurring algorithms[C]//European Conference on Computer Vision.2020.
[154]LEE J,SON H,RIM J,et al.Iterative filter adaptive network for single image defocus deblurring[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:2034-2042.
[155]LI H,ZHANG Z,JIANG T,et al.Real-World Deep Local Motion Deblurring[J].Proceedings of the AAAI Conference on Artificial Intelligence,2023,37(1):1314-1322.
[156]RIM J,KIM G,KIM J,et al.Realistic Blur Synthesis for Learning Image Deblurring[J].arXiv:2202.08771,2022.
[157]ABUOLAIM A,DELBRACIO M,KELLY D,et al.Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data[C]//ICCV.2021.
[158]ZHANG H,DAI Y,LI H,et al.Deep Stacked HierarchicalMulti-patch Network for Image Deblurring[C]//IEEE Conference on Computer Vision and Pattern Recognition.2019.
[159]PARK P D,KANG D U,KIM J,et al.Multi-temporal recurrent neural networks for progressive non-uniform single image deblurring with incremental temporal training[C]//European Conference on Computer Vision.2020.
[160]ZAMIR S W,ARORA A,KHAN S H,et al.Multi-Stage Progressive Image Restoration[C]//CVPR.2021.
[161]CHEN L,LU X,ZHANG J,et al.HINet:Half instance normalization network for image restoration[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:182-192.
[162]WANG Z,CUN X,BAO J,et al.Uformer:A General U-Shaped Transformer for Image Restoration[C]//CVPR.2022.
[163]KONG L,DONG J,GE J,et al.Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring[C]//CVPR.2023.
[164]FANG Z,WU F,DONG W,et al.Self-supervised Non-uniform Kernel Estimation with Flow-based Motion Prior for Blind Image Deblurring[C]//CVPR.2023.
[165]DONG J,PAN J,YANG Z,et al.Multi-Scale Residual Low-Pass Filter Network for Image Deblurring[C]//ICCV.2023.
[166]ZAMIR S W,ARORA A,KHAN S,et al.Restormer:Efficient Transformer for High-Resolution Image Restoration[C]//CVPR.2022.
[167]CHO S J,JI S W,HONG J P,et al.Rethinking coarse-to-fine approach in single image deblurring[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:4641-4650.
[168]WHANG J,DELBRACIO M,TALEBI H,et al.Deblurring via Stochastic Refinement[C]//CVPR.2022.
[169]TSAI F J,PENG Y T,LIN Y Y,et al.Stripformer:Strip Transformer for Fast Image Deblurring[C]//ECCV.2022.
[170]MAO X,LIU Y,LIU F,et al.Intriguing Findings of Frequency Selection for Image Deblurring[C]//AAAI.2023.
[171]MAO X,LI Q,WANG Y.AdaRevD:Adaptive Patch ExitingReversible Decoder Pushes the Limit of Image Deblurring[J].arXiv:2406.09135,2024.
[172]KARAALI A,JUNG C R.Edge-based defocus blur estimation with adaptive scale selection[J].IEEE Transactions on Image Processing,2018,27(3):1126-1137.
[173]LEE J,LEE S,CHO S,et al.Deep Defocus Map EstimationUsing Domain Adaptation[C]//IEEE Conference on Computer Vision and Pattern Recognition.2019.
[174]SHI J,XU L,JIA J.Just noticeable defocus blur detection and estimation[C]//CVPR.2015.
[175]SON H,LEE J,CHO S,et al.Single Image Defocus Deblurring Using Kernel-Sharing Parallel Atrous Convolutions[C]//ICCV.2021.
[176]CUI Y,REN W,CAO X,et al.Revitalizing Convolutional Network for Image Restoration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,46(12):9423-9438.
[177]CUI Y,TAO Y,BING Z,et al.Selective Frequency Network for Image Restoration[C]//The Eleventh International Conference on Learning Representations.2023.
[178]CUI Y,REN W,CAO X,et al.Image Restoration via Frequency Selection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,46(2):1093-1108.
[179]GUO H,LI J,DAI T,et al.MambaIR:A Simple Baseline for Image Restoration with State-Space Model[J].arXiv:2402.15648,2024.
[180]LI Y W,FAN Y C,XIANG X Y,et al.Efficient and Explicit Modelling of Image Hierarchies for Image Restoration[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2023.
[181]GAO H,DANG D.Learning Enriched Features via SelectiveState Spaces Model for Efficient Image Deblurring[J].arXiv:2403.20106,2024.
[182]OPENAI,ACHIAM J,ADLER S,et al.GPT-4 Technical Report[J].arXiv:2303.08774,2023.
[183]DEVLIN J,CHANG M W,LEE K,et al.BERT:Pre-training of Deep Bidirectional Transformers for Language Understanding[J].arXiv:1810.04805,2018.
[184]RAMESH A,PAVLOV M,GOH G,et al.Zero-Shot Text-to-Image Generation[J].arXiv:2102.12092,2021.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed