Computer Engineering and Applications ›› 2020, Vol. 56 ›› Issue (19): 34-41.DOI: 10.3778/j.issn.1002-8331.2005-0393

Previous Articles     Next Articles

Research Progress of Image Super-Resolution Methods

XIE Haiping, XIE Kaili, YANG Haitao   

  1. 1.Graduate School, Space Engineering University, Beijing 101416, China
    2.School of Space Information, Space Engineering University, Beijing 101416, China
  • Online:2020-10-01 Published:2020-09-29

图像超分辨率方法研究进展

谢海平,谢凯利,杨海涛   

  1. 1.航天工程大学 研究生院,北京 101416
    2.航天工程大学 航天信息学院,北京 101416

Abstract:

With the development of computer theory and technology, image super-resolution theory and technology have continuously made new progress, and a series of methods such as interpolation, reconstruction and machine learning have been developed. This paper reports the research progress of image super-resolution. Firstly, it introduces the methods of image super-resolution. Secondly, it summarizes major deep learning super-resolution models and the current development trend of image super-resolution. Finally, the future development and challenges of super-resolution research are proposed.

Key words: super-resolution, image reconstruction, deep learning

摘要:

随着计算机理论与技术的发展,图像超分辨率理论和技术手段不断取得新的进步,发展出插值法、重构法和学习法等一系列方法。报告了图像超分辨率的研究进展,梳理了主要的图像超分辨率方法,阐述了几种较为重要的深度学习超分辨率模型,总结了当前图像超分辨率的发展趋势,对超分辨率的研究提出了展望。

关键词: 超分辨率, 图像重构, 深度学习