计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (24): 51-60.DOI: 10.3778/j.issn.1002-8331.2105-0418

• 热点与综述 • 上一篇    下一篇

图像超分辨率深度学习研究及应用进展

夏皓,吕宏峰,罗军,蔡念   

  1. 1.工业和信息化部电子第五研究所,广州 511370
    2.广东工业大学 信息工程学院,广州 510006
  • 出版日期:2021-12-15 发布日期:2021-12-13

Survey on Deep Learning Based Image Super-Resolution

XIA Hao, LYU Hongfeng, LUO Jun, CAI Nian   

  1. 1.China Electronic Product Reliability and Environment Testing Research Institute, The Fifht Eletronic Research Institute of MIIT, Guangzhou 511370, China
    2.School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China
  • Online:2021-12-15 Published:2021-12-13

摘要:

图像超分辨率重建是用低分辨率图像重建出对应的高分辨率图像的过程。目前,图像超分辨率技术已经成功应用于计算机视觉和图像处理领域。近年来,由于深度学习具有能够从大量数据中自动学习特征的能力,因此被广泛应用于图像超分辨率领域中。介绍了图像超分辨重建的背景,详细总结了用于图像超分辨率的深度学习模型,阐述了图像超分辨率技术在卫星遥感图像、医学影像、视频监控、工业检测任务方面的应用。总结了图像超分辨算法的当前研究现状以及未来发展方向。

关键词: 图像超分辨率, 深度学习, 卷积神经网络, 生成对抗网络

Abstract:

Image super-resolution reconstruction is the process of using low-resolution images to reconstruct the corresponding high-resolution images. At present, image super-resolution technology has been successfully applied in the fields of computer vision and image processing. In recent years, due to deep learning’s ability of self-learning from a large amount of data, it has been widely used in the field of image super-resolution. This article introduces the background of image super-resolution reconstruction, and summarizes the deep learning based image super-resolution model in detail, and then elaborates the image super-resolution technology in satellite remote sensing images, medical imaging, video surveillance, and industrial inspection tasks application. Finally, this article summarizes the current research status and future development directions of image super-resolution algorithms.

Key words: image super-resolution, deep learning, convolutional neural network, generative adversarial network