The Application of Deep Learning in Image Deblurring
Authors: 
Chengchao Jiang, Lei Hu, Guotao JiaAuthors Info & Claims
Chengchao Jiang, Lei Hu, Guotao JiaAuthors Info & ClaimsPages 1075 - 1079
Abstract
Images are an important medium for people to obtain information. In the process of acquiring images, it is inevitable that images will become blurred due to various reasons. Image restoration is a technical method that uses algorithms to enhance image quality and is an important research field in computer vision. It is widely used in industrial, agricultural, and medical image processing. In recent years, with the rapid development of deep learning technology, an increasing number of image restoration algorithms based on deep neural networks have been proposed. This paper mainly introduces image restoration technology based on deep neural networks from the perspective of image deblurring. The paper first elaborates on the overall classification of image restoration algorithms, then discusses the causes of image blurring and commonly used traditional algorithms, deep learning algorithms, and models. Finally, the paper summarizes the advantages and disadvantages of various image restoration methods and prospects for the future development of image restoration technology.
References
[1]
Richardson W H. 1972. Bayesian-based iterative method of image restoration. Journal of the Optical Society of America. Optica Publishing Group, 55–59.
[2]
Lucy L B. 1974. An iterative technique for the rectification of observed distributions. The Astronomical Journal. IOP Publishing, 745–754.
[3]
Fu Yuan. 2020. Design of a Mine Surveillance Image Restoration Device Based on the L-R Algorithm. Industrial and Mining Automation. China Coal Science and Technology Group Chongqing Research Institute Co., Ltd., 101–105.
[4]
Liu Wenlong, Liu Xuebin, Wang Shuang, et al. 2022. Holographic Coding Spectral Imaging Data Reconstruction Based on Diffraction Theory. Acta Physica Sinica. Chinese Physical Society, 146–155.
[5]
Ji Baibing, Cao Qixin. 2021. A Real-time Monocular 3D Reconstruction System for Robot Grasping. Mechanical Design and Manufacturing. Mechanical Industry Information Research Institute, 287–290.
[6]
Zhao Bo, Zhang Wensheng, Ding Huan. 2011. A New Image Deblurring Algorithm Based on Richardson-Lucy. Computer Engineering and Applications. China North Industries Group Corporation Fifty-Ninth Research Institute, 1–4.
[7]
Zhang Jianguo, Tuo Yangyang, Jiang Ruijiao, et al. 2020. Improvement of the Richardson-Lucy Algorithm in Blur Image Restoration. Journal of Metrology. China National Institute of Metrology, 153–158.
[8]
Feng Wei, Liu Guangyu, Liu Biao, et al. 2024. A Sonar Image Denoising Algorithm Based on Adaptive Wiener Filtering and 2D-VMD. Journal of Nanjing University of Information Science & Technology. Nanjing University of Information Science & Technology, 97–105.
[9]
Song Zijian. 2023. Real-time Sonar Image Enhancement Based on CLAHE and Wiener Filtering. Electroacoustic Technology. China Electronics Technology Group Corporation Third Research Institute, 27–29.
[10]
Ju Yifeng, Gao Yisong, Chen Jun'an, et al. 2023. Image Recognition Method of Transmission Line Hidden Danger Areas Based on DCNN. Electronic Design Engineering. China Electronics Technology Group Corporation Twenty-seventh Research Institute, 182–185.
[11]
Zhu Xufei, Tong Chunchu. 2023. Research on a Fast Fabric Density Detection Method Based on Image Processing. China Textile Inspection. China Fiber Inspection Bureau, 83–85.
[12]
Ma Tao, Liu Qiumei. 2023. A Method for Restoring Blurred Sports Video Images Based on Wiener Filtering. Automation Technology and Applications. Chinese Association of Automation, 123–126.
[13]
Wang Min, Zhou Shudao, Liu Zhanhua, et al. 2020. Restoration of Imaging Blur in Atmospheric Visibility Detection by Image Method. Science and Technology Engineering. China Association for Science and Technology, 3668–3674.
[14]
Xiao Zhenyu, Yu Shuchun, Liu Shuang, et al. 2017. A Motion Blur Instrument Image Restoration Algorithm Based on Improved Wiener Filtering. Electrical Measurement and Instrumentation. Chinese Instrument and Meter Society, 88–91.
[15]
Krizhevsky A, Sutskever I, Hinton G E. 2012. ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems. Curran Associates, Inc., 1097–1105.
[16]
Long J, Shelhamer E, Darrell T. 2015. Fully convolutional networks for semantic segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 3431–3440.
[17]
Nah S, Kim T H, Lee K M. 2017. Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring. IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 257–265.
[18]
Zeng An, Wang Lieji, Pan Dan, et al. 2020. Research on Medical Image Registration Technology Based on FCN and Mutual Information. Computer Engineering and Applications. China North Industries Group Corporation Fifty-Ninth Research Institute, 202–208.
[19]
Duan Jie, Cui Zhiming, Shen Yi, et al. 2020. An Improved FCN Method for Liver Tumor CT Image Segmentation. Journal of Graphics. China Graphics Society, 100–107.
[20]
Adke D, Karnik A, Berman H, Mathi S. 2021. Detection and Blur-Removal of Single Motion Blurred Image using Deep Convolutional Neural Network. 2021 International Conference on Artificial Intelligence and Computer Science Technology (ICAICST). IEEE, 79–83.
[21]
Lim W L, et al. 2023. Performance Assessment of U-Net for Semantic Segmentation of Liquid Spray Images with Gaussian Blurring. 2023 IEEE International Conference on Computing (ICOCO). IEEE, 462–467.
[22]
Wang Z, Xue X, Ma L, Fan X. 2020. Underwater image enhancement based on dual U-net. 2020 8th International Conference on Digital Home (ICDH). IEEE, 141–146.
[23]
Bendre S, Kaul S, Ghosh S, Pujari S, Mahajan D, Bendre V. 2023. Attention U-Net for Low Light Image Enhancement. 2023 7th International Conference On Computing, Communication, Control And Automation (ICCUBEA). IEEE, 1–4.
[24]
Goodfellow I, Pouget-Abadie J, Mirza M. 2014. Generative adversarial nets. Advances in neural information processing systems. Curran Associates, Inc., 2672–2680.
[25]
Kupyn O, Budzan V, Mykhailych M. 2018. DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 8183–8192.
[26]
Cheng Xiaorong, Cheng Yuanyuan. 2023. An Insulator Image Dehazing Algorithm Based on Improved DeblurGAN Network. Electric Power Science and Engineering. State Grid Electric Power Research Institute, 39–47.
[27]
Peng Ning, Wu Hao, Qi Ziyuan, et al. 2023. An Image Denoising and Enhancement Algorithm for the Surface Defects of Electronic Commutators. Journal of Hebei University of Water Conservancy and Electric Power. Hebei University of Engineering, 1–8.
[28]
Liang Z, Yang B, Xiao H. 2020. Using Motion Deblurring Algorithm to Improve Vehicle Recognition via DeblurGAN. 2020 International Conference on Virtual Reality and Intelligent Systems (ICVRIS). IEEE, 486–489.
[29]
Fu Zhensha, Peng Jinhui, Zeng Yanjie, et al. 2022. Assessment Method for the Use of Traffic Markings for Autonomous Driving Vehicles. Journal of South China University of Technology (Natural Science Edition). South China University of Technology, 1–13.
[30]
Truong N Q, Lee Y W, Owais M. 2020. SlimDeblurGAN-Based Motion Deblurring and Marker Detection for Autonomous Drone Landing. Sensors. MDPI, 3918.
[31]
Liu Ping, Liu Chuancai, Zhang Jialuo. 2020. Image De-motion Blurring Technology with Residual Separated Convolutional Neural Network. Computer and Digital Engineering. China Shipbuilding Industry Corporation The Seven Hundred and Ninth Research Institute, 1975–1980.
Index Terms
- The Application of Deep Learning in Image Deblurring
Recommendations
Deep non-blind deblurring network for saturated blurry images
AbstractNon-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 ...
Spatially variant defocus blur map estimation and deblurring from a single image
A blur map estimation method using edge information is proposed.The blur map is segmented into multiple superpixels according to the image contours.Ringing artifacts and noise are detected and removed after deconvolution. In this paper, we propose a ...
Deep Image Deblurring: A Survey
AbstractImage deblurring is a classic problem in low-level computer vision with the aim to recover a sharp image from a blurred input image. Advances in deep learning have led to significant progress in solving this problem, and a large number of ...
Comments
Information & Contributors
Information
Published In
June 2024
1206 pages
ISBN:9798400710247
DOI:10.1145/3690407
Copyright © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 24 October 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
CAIBDA 2024
CAIBDA 2024: 2024 4th International Conference on Artificial Intelligence, Big Data and Algorithms
June 21 - 23, 2024
Zhengzhou, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 51Total Downloads
- Downloads (Last 12 months)51
- Downloads (Last 6 weeks)10
Reflects downloads up to 03 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderFull Text
View this article in Full Text.
Full TextHTML Format
View this article in HTML Format.
HTML Format