A Review of Single Image Super-Resolution Reconstruction Based on Deep Learning

被引：0
作者：
Wu J. [1 ,2 ]
Ye X.-J. [1 ,2 ]
Huang F. [1 ,2 ]
Chen L.-Q. [1 ,2 ]
Wang Z.-F. [1 ,2 ]
Liu W.-X. [2 ,3 ]
机构：
[1] School of Mechanical Engineering and Automation, Fuzhou University, Fujian, Fuzhou
[2] Advanced Technology Innovation Institute, Fuzhou University, Fujian, Fuzhou
[3] College of Computer and Data Science, Fuzhou University, Fujian, Fuzhou
来源：
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2022年 / 50卷 / 09期
关键词：
challenges; convolutional neural network; deep learning; generative adversarial network; single image; super-resolution reconstruction; transformer;
D O I：
10.12263/DZXB.20220091
中图分类号：
学科分类号：
摘要：
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 comprehensive⁃ ly reviews the technical architecture and research process of deep-learning-based single image super-resolution reconstruc⁃ tion, 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 adversari⁃ al 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 super-resolution reconstruction is prospected according to the related content of network model and super-resolution reconstruc⁃ tion challenges. © 2022 Chinese Institute of Electronics. All rights reserved.
引用
收藏
页码：2265 / 2294
页数：29
相关论文
共 158 条
  • [1] DAI D X, WANG Y J, CHEN Y H, Et al., Is image super-resolution helpful for other vision tasks?, 2016 IEEE Winter Conference on Applications of Computer Vision, pp. 1-9, (2016)
  • [2] BAI Y C, ZHANG Y Q, DING M L, Et al., SOD-MTGAN: Amall object detection via multi-task generative adversari⁃ al network, Proceedings of the European Conference on Computer Vision(ECCV 2018), pp. 210-226, (2018)
  • [3] BEI Y J, DAMIAN A, HU S J, Et al., New techniques for preserving global structure and denoising with low infor⁃ mation loss in single-image super-resolution, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW), pp. 987-9877, (2018)
  • [4] WU X X, XIAO S, ZHANG Y., Registration based super-resolution reconstruction for lung 4D-CT image, Acta Electronica Sinica, 43, 2, pp. 383-386, (2015)
  • [5] YIN Y, ROBINSON J, ZHANG Y L, Et al., Joint super-res⁃ olution and alignment of tiny faces, Proceedings of the AAAI Conference on Artificial Intelligence, 34, 7, pp. 12693-12700, (2020)
  • [6] HUANG Y W, ZHENG F, WANG D Y, Et al., Super-reso⁃ lution and inpainting with degraded and upgraded genera⁃ tive adversarial networks, Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelli⁃ gence, pp. 645-651, (2021)
  • [7] WANG Z Y, JIANG K, YI P, Et al., Ultra-dense GAN for satellite imagery super-resolution, Neurocomputing, 398, pp. 328-337, (2020)
  • [8] GAO G W, YU Y, XIE J, Et al., Constructing multilayer lo⁃ cality-constrained matrix regression framework for noise robust face super-resolution, Pattern Recognition, 110, (2021)
  • [9] LI Y H, WANG Z, ZHANG K B, Et al., Survey on example learning-based single image super-resolution technique, Computer Engineering and Applications, 54, 15, pp. 13-21, (2018)
  • [10] SUN X, LI X G, LI J F, Et al., Review on deep learning based image super-resolution restoration algorithms, Acta Automatica Sinica, 43, 5, pp. 697-709, (2017)
12345678910