帮助 关于我们

返回检索结果

基于深度学习的单帧图像超分辨率重建综述
A Review of Single Image Super-Resolution Reconstruction Based on Deep Learning

查看参考文献158篇

吴靖 1,2   叶晓晶 1,2   黄峰 1,2 *   陈丽琼 1,2   王志锋 1,2   刘文犀 2,3  
文摘 图像超分辨率重建是计算机视觉中的基本图像处理技术之一,不仅可以提高图像分辨率改善图像质量,还可以辅助其他计算机视觉任务.近年来,随着人工智能浪潮的兴起,基于深度学习的图像超分辨率重建也取得了显著进展.本文在简述图像超分辨率重建方法的基础上,全面综述了基于深度学习的单帧图像超分辨率重建的技术架构及研究历程,包括数据集构建方式、网络模型基本框架以及用于图像质量评估的主、客观评价指标,重点介绍了根据网络结构及图像重建效果划分的基于卷积神经网络的方法、基于生成对抗网络的方法以及基于Transformer的方法,并对相关网络模型加以评述和对比,最后依据网络模型和超分辨率重建挑战赛相关内容,展望了图像超分辨率重建未来的发展趋势.
其他语种文摘 Image super-resolution reconstruction is one of the basic image processing techniques in computer vision, which can not only improve image resolution and image quality, but also assist other computer vision tasks. In recent years, with the rise of artificial intelligence, deep-learning-based image super-resolution reconstruction has also made remarkable progress. Based on a brief description of the image super-resolution reconstruction methodology, this paper comprehensively reviews the technical architecture and research process of deep-learning-based single image super-resolution reconstruction, including the method of datasets construction, the basic framework of the network model, the subjective and objective evaluation metrics for image quality evaluation. The methods based on convolutional neural networks, generative adversarial networks and Transformer, which are divided according to network structure and image reconstruction effect are mainly introduced, and related network models are reviewed and compared. Finally, the future development trend of image superresolution reconstruction is prospected according to the related content of network model and super-resolution reconstruction challenges.
来源 电子学报 ,2022,50(9):2265-2294 【核心库】
DOI 10.12263/DZXB.20220091
关键词 超分辨率重建 ; 深度学习 ; 单帧图像 ; 卷积神经网络 ; 生成对抗网络 ; Transformer ; 挑战赛
地址

1. 福州大学机械工程及自动化学院, 福建, 福州, 350116  

2. 福州大学先进技术创新研究院, 福建, 福州, 350116  

3. 福州大学计算机与大数据学院, 福建, 福州, 350116

语种 中文
文献类型 综述型
ISSN 0372-2112
学科 自动化技术、计算机技术
基金 国家自然科学基金
文献收藏号 CSCD:7323076

参考文献 共 158 共8页

1.  Dai D X. Is image superresolution helpful for other vision tasks?. 2016 IEEE Winter Conference on Applications of Computer Vision,2016:1-9 CSCD被引 1    
2.  Bai Y C. SOD-MTGAN: Amall object detection via multi-task generative adversarial network. Proceedings of the European Conference on Computer Vision(ECCV 2018),2018:210-226 CSCD被引 1    
3.  Bei Y J. New techniques for preserving global structure and denoising with low information loss in single-image super-resolution. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW),2018:987-9877 CSCD被引 1    
4.  吴秀秀. 基于配准的肺4D-CT图像超分辨率重建. 电子学报,2015,43(2):383-386 CSCD被引 5    
5.  Yin Y. Joint super-resolution and alignment of tiny faces. Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(7):12693-12700 CSCD被引 1    
6.  Huang Y W. Super-resolution and inpainting with degraded and upgraded generative adversarial networks. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence,2021:645-651 CSCD被引 1    
7.  Wang Z Y. Ultra-dense GAN for satellite imagery super-resolution. Neurocomputing,2020,398:328-337 CSCD被引 6    
8.  Gao G W. Constructing multilayer locality-constrained matrix regression framework for noise robust face super-resolution. Pattern Recognition,2021,110:107539 CSCD被引 1    
9.  李云红. 基于学习的图像超分辨重建方法综述. 计算机工程与应用,2018,54(15):13-21 CSCD被引 9    
10.  孙旭. 基于深度学习的图像超分辨率复原研究进展. 自动化学报,2017,43(5):697-709 CSCD被引 38    
11.  刘颖. 图像超分辨率技术的回顾与展望. 计算机科学与探索,2020,14(2):181-199 CSCD被引 14    
12.  Harris J L. Diffraction and resolving power. Journal of the Optical Society of America,1964,54(7):931-936 CSCD被引 88    
13.  Goodman J W. Introduction to fourier optics. Physics Today,1969,22(4):97-101 CSCD被引 2    
14.  Tsai R Y. Multiframe image restoration and registration. Advances in Computer Vision and Image Processing,1984,1(2):317-339 CSCD被引 118    
15.  Duchon C E. Lanczos filtering in one and two dimensions. Journal of Applied Meteorology,1979,18(8):1016-1022 CSCD被引 206    
16.  Keys R. Cubic convolution interpolation for digital image processing. IEEE Transactions on Acoustics, Speech, and Signal Processing,1981,29(6):1153-1160 CSCD被引 252    
17.  Stark H. High-resolution image recovery from image-plane arrays, using convex projections. Journal of the Optical Society of America. A, Optics and Image Science,1989,6(11):1715-1726 CSCD被引 142    
18.  Irani M. Improving resolution by image registration. CVGIP: Graphical Models and Image Processing,1991,53(3):231-239 CSCD被引 211    
19.  Schultz R R. A Bayesian approach to image expansion for improved definition. IEEE Transactions on Image Processing,1994,3(3):233-242 CSCD被引 81    
20.  伍政华. 基于二阶广义方向性全变分的图像超分辨率重建方法. 电子学报,2017,45(11):2625-2632 CSCD被引 3    
引证文献 7

1 陈纯毅 多尺度注意力融合的图像超分辨率重建 中国光学(中英文),2023,16(5):1034-1044
CSCD被引 0 次

2 朱新峰 轻量级图像超分辨率研究综述 计算机工程与应用,2024,60(16):49-60
CSCD被引 0 次

显示所有7篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护:中国科学院文献情报中心
地址:北京中关村北四环西路33号 邮政编码:100190 联系电话:(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号