Advertisement

Single-Image Super-Resolution: A Survey

  • Tingting Yao
  • Yu Luo
  • Yantong Chen
  • Dongqiao Yang
  • Lei ZhaoEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 516)

Abstract

Single-image super-resolution has been broadly applied in many fields such as military term, medical imaging, etc. In this paper, we mainly focus on the researches of recent years and classify them into non-deep learning SR algorithms and deep learning SR algorithms. For each classification, the basic concepts and algorithm processes are introduced. Furthermore, the paper discusses the advantages and disadvantages of different algorithms, which will offer potential research direction for the future development of SR.

Keywords

Single-image super-resolution Learning-based Deep learning Survey 

Notes

Acknowledgments

This work was supported by the National Natural Science Foundation of China (No. 31700742), the Young Elite Scientist Sponsorship Program by CAST (2017QNRC001) and the Fundamental Research Funds for the Central Universities (No. 3132018306, 3132018180, 3132018172).

References

  1. 1.
    Ahmed J, Shah MA. Single image super-resolution by directionally structured coupled dictionary learning. Eurasip J Image Video Process. 2016;1:36.Google Scholar
  2. 2.
    Ahmed J, Klette R. Coupled multiple dictionary learning based on edge sharpness for single-image super-resolution. In: International conference on pattern recognition. IEEE; 2017.Google Scholar
  3. 3.
    Chang H, Yeung DY, Xiong Y. Super-resolution through neighbor embedding.  Proc Comput Vis Pattern Recogn. 2004;1:I-275–82.Google Scholar
  4. 4.
    Dong C, et al. Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell. 2016;38(2):295–307.CrossRefGoogle Scholar
  5. 5.
    Freeman WT, Jones TR, Pasztor EC. Example-based super-resolution. Comput Graph Appl. 2002;2:56–65 (IEEE22.).CrossRefGoogle Scholar
  6. 6.
    Gu S, et al. Convolutional sparse coding for image super-resolution. In: IEEE international conference on computer vision. IEEE; 2015. p. 1823–31.Google Scholar
  7. 7.
    Huang JB, Singh A, Ahuja N. Single image super-resolution from transformed self-exemplars. Comput Vis Pattern Recogn. 2015:5197–206.Google Scholar
  8. 8.
    Kim J, Lee JK, Lee KM. Accurate image super-resolution using very deep convolutional networks. Comput Vis Pattern Recogn. 2016:1646–54.Google Scholar
  9. 9.
    Kim J, Lee JK, Lee KM. Deeply-recursive convolutional network for image super-resolution. Comput Vis Pattern Recogn. 2016:1637–45.Google Scholar
  10. 10.
    Krishnan D, Fergus R. Fast image deconvolution using hyper-Laplacian priors. In: International conference on neural information processing systems Curran Associates Inc.; 2009. p. 1033–41.Google Scholar
  11. 11.
    Li X, et al. Single image super-resolution via subspace projection and neighbor embedding.  Neurocomputing. 2014;139:310–20.CrossRefGoogle Scholar
  12. 12.
    Liang Y, et al. Incorporating image priors with deep convolutional neural networks for image super-resolution. Neurocomputing. 2016;194:340–7.CrossRefGoogle Scholar
  13. 13.
    Song S, et al. Joint sub-band based neighbor embedding for image super-resolution. In: IEEE international conference on acoustics, speech and signal processing. IEEE; 2016. p. 1661–5.Google Scholar
  14. 14.
    Sun X, Xiao-Guang LI, Jia-Feng LI, et al. Review on deep learning based image super-resolution restoration algorithms. Acta Automatica Sin. 2017;43(5):697–709.Google Scholar
  15. 15.
    Timofte R, Rothe R, Gool LV. Seven ways to improve example-based single image super resolution; 2015. p. 1865–73.Google Scholar
  16. 16.
    Timofte R, Smet VD, Gool LV. A+: Adjusted anchored neighborhood regression for fast super-resolution. In: Asian conference on computer vision. Springer, Cham; 2014. p. 111–26.Google Scholar
  17. 17.
    Wang Z, Yang Y, Wang Z, et al. Learning super-resolution jointly from external and internal examples. IEEE Trans Image Process. (A Publication of the IEEE Signal Processing Society). 2015;24(11):4359.MathSciNetCrossRefGoogle Scholar
  18. 18.
    Yang J, et al. Image super-resolution via sparse representation. IEEE Trans Image Proces. 2010;19(11):2861–73.Google Scholar
  19. 19.
    Yang W, et al. Deep edge guided recurrent residual learning for image super-resolution. IEEE Trans Image Process (A Publication of the IEEE Signal Processing Society). 2016;26(12):5895–907.MathSciNetCrossRefGoogle Scholar
  20. 20.
    Yang W, et al. Image super-resolution via nonlocal similarity and group structured sparse representation. Vis Commun Image Process. 2016:1–4.Google Scholar
  21. 21.
    Zhang Y, et al. Image super-resolution based on, structure-modulated sparse representation. IEEE Trans Image Process. 2015;24(9):2797–810.MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Tingting Yao
    • 1
  • Yu Luo
    • 1
  • Yantong Chen
    • 1
  • Dongqiao Yang
    • 1
  • Lei Zhao
    • 2
    Email author
  1. 1.College of Information Science and Technology, Collaborative Innovation Research Institute of Autonomous ShipDalian Maritime UniversityDalianChina
  2. 2.Institute of Environmental Systems Biology, College of Environmental Science and EngineeringDalian Maritime UniversityDalianChina

Personalised recommendations