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
  • [21] WANG X H, ZHAO X Y, BI X Y, Et al., Single image su⁃ per-resolution reconstruction approach based on multi-an⁃ gle contour templates variational calculus model in wave⁃ let domain, Acta Electronica Sinica, 46, 9, pp. 2256-2262, (2018)
  • [22] FREEMAN W T, PASZTOR E C, CARMICHAEL O T., Learning low-level vision, International Journal of Computer Vision, 40, pp. 25-47, (2000)
  • [23] CHANG H, YEUNG D Y, XIONG Y M., Super-resolu⁃ tion through neighbor embedding, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 275-282, (2004)
  • [24] YANG J C, WRIGHT J, HUANG T, Et al., Image super-resolution as sparse representation of raw image patches, 2008 IEEE Conference on Computer Vision and Pat⁃ tern Recognition, pp. 1-8, (2008)
  • [25] TIMOFTE R, DE V, GOOL L V., Anchored neighbor⁃ hood regression for fast example-based super-resolution, 2013 IEEE International Conference on Computer Vision, pp. 1920-1927, (2013)
  • [26] PAN Z X, YU J, XIAO C B, Et al., Single image super res⁃ olution based on adaptive multi-dictionary learning, Acta Electronica Sinica, 43, 2, pp. 209-216, (2015)
  • [27] PARK S C, PARK M K, KANG M G., Super-resolution image reconstruction: A technical overview, IEEE Sig⁃ nal Processing Magazine, 20, 3, pp. 21-36, (2003)
  • [28] JIANG J, ZHANG X S., A review of super-resolution re⁃ construction algorithms, Infrared Technology, 34, 1, pp. 24-30, (2012)
  • [29] SU H, ZHOU J, ZHANG Z H., Survey of super-resolution image reconstruction methods, Acta Automatica Sini⁃ ca, 39, 8, pp. 1202-1213, (2013)
  • [30] YANG W M, ZHANG X C, TIAN Y P, Et al., Deep learn⁃ ing for single image super-resolution: A brief review, IEEE Transactions on Multimedia, 21, 12, pp. 3106-3121, (2019)
12345678910