计算机工程与应用 ›› 2017, Vol. 53 ›› Issue (16): 29-35.DOI: 10.3778/j.issn.1002-8331.1705-0097

• 热点与综述 • 上一篇    下一篇

图像超分辨率重建的研究进展

曾  凯1,丁世飞1,2   

  1. 1.中国矿业大学 计算机科学与技术学院,江苏 徐州 221116
    2.中国科学院计算技术研究所 智能信息处理重点实验室,北京 100190
  • 出版日期:2017-08-15 发布日期:2017-08-31

Advances in image super-resolution reconstruction

ZENG Kai1, DING Shifei1,2   

  1. 1.School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China
    2.Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
  • Online:2017-08-15 Published:2017-08-31

摘要: 图像超分辨率重建技术对于输入的低分辨率图像进行相关处理,从而重构出高分辨率图像,该技术已经成为图像处理研究领域的一个热点方向。对超分辨率图像重建的研究进展进行了综述。阐述了图像超分辨率重建的基本原理。对基于重建的图像超分辨重建中:IBP,POCS等算法,基于学习的图像超分辨率重建中:稀疏表示,基于深度神经网络等算法及一些相关改进的算法进行了综述。对图像超分辨率重建的研究提出了展望。

关键词: 图像, 超分辨率, 重建

Abstract: Image super-resolution reconstruction technology is to deal with the input low resolution image, so as to reconstruct the high resolution image, which has become a hotspot in the field of image processing. In this paper, the research progress of image super-resolution reconstruction is reviewed. Firstly, the basic principle of image super-resolution reconstruction is described. Secondly, the algorithms of IBP and POCS in image super-resolution reconstruction based on reconstruction, the algorithms of sparse representation and deep neural network in super-resolution reconstruction based on learning and some related algorithms are reviewed. Finally, the prospect of image super-resolution reconstruction is proposed.

Key words: image, super-resolution, reconstruction