Review on Deep Learning Based Image Super-resolution Restoration Algorithms

被引：0
|
作者：
Sun X. [1 ]
Li X.-G. [1 ]
Li J.-F. [1 ]
Zhuo L. [1 ]
机构：
[1] Signal & Information Processing Laboratory, Beijing University of Technology, Beijing
来源：
Li, Xiao-Guang (lxg@bjut.edu.cn) | 1600年 / Science Press卷 / 43期
关键词：
Convolutional neural network (CNN); Deep neural networks; Recurrent neural network; Super resolution restoration (SR);
D O I：
10.16383/j.aas.2017.c160629
中图分类号：
学科分类号：
摘要：
Super resolution image restoration technology is a hot field of image processing in the field of video surveillance, image processing, forensic analysis, with a wide range of application requirements. In recent years, the rapid development of deep learning in the field of multimedia processing, deep learning based super-resolution images restoration has gradually become a mainstream technology. This paper reviews the existing deep learning based image super-resolution restoration work. In terms of network type, network structure, and training methods, the advantages and disadvantages of the prior art are analyzed and the development contexts are sorted out. On this basis, the paper further points out the future direction of the restoration technique based on deep learning of the super-resolution image. Copyright © 2017 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：697 / 709
页数：12
相关论文
共 54 条
  • [1] Zhuo L., Wang S.-Y., Li X.-G., Image/Video Super Resolution, (2011)
  • [2] Zhang X.-L., Research on compression and super reso-lution of remote sensing imagery, (2006)
  • [3] Baker S., Kanade T., Limits on super-resolution and how to break them, Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition, 2, pp. 372-379, (2000)
  • [4] Van Ouwerkerk J.D., Image super-resolution survey, Image and Vision Computing, 24, 10, pp. 1039-1052, (2006)
  • [5] Su H., Zhou J., Zhang Z.-H., Survey of super-resolution image reconstruction methods, Acta Automatica Sinica, 39, 8, pp. 1202-1213, (2013)
  • [6] Harris J.L., Diffraction and resolving power, Journal of the Optical Society of America, 54, 7, pp. 931-936, (1964)
  • [7] Goodman J.W., Introduction to Fourier Optics, (1968)
  • [8] Tsai R.Y., Huang T.S., Multiple frame image restoration and registration, Advances in Computer Vision and Image Processing, pp. 317-339, (1984)
  • [9] Aly H., Dubois E., Regularized image up-sampling using a new observation model and the level set method, Proceedings of the 2003 International Conference on Image Processing, 2, (2003)
  • [10] Aly H.A., Dubois E., Image up-sampling using total-variation regularization with a new observation model, IEEE Transactions on Image Processing, 14, 10, pp. 1647-1659, (2005)
123456