Computer Engineering and Applications ›› 2021, Vol. 57 ›› Issue (17): 1-9.DOI: 10.3778/j.issn.1002-8331.2103-0556

Previous Articles     Next Articles

Overview of Image Super-Resolution Algorithms

SUN Jingyang, CHEN Fengdong, HAN Yueyue, WU Yuwen, GAN Yu, LIU Guodong   

  1. School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150001, China
  • Online:2021-09-01 Published:2021-08-30

图像超分辨率重建算法综述

孙菁阳,陈凤东,韩越越,吴煜雯,甘雨,刘国栋   

  1. 哈尔滨工业大学 仪器科学与工程学院,哈尔滨 150001

Abstract:

Image super-resolution reconstruction aims to recover high-resolution and clear images from low-resolution images. This article first explains the idea of typical image super-resolution reconstruction methods, and then reviews typical and latest image super-resolution reconstruction algorithms based on deep learning from the dimensions of up-sampling position and up-sampling method, learning strategy, loss function, etc. It analyzes the latest development status, and looks forward to the future development trend.

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

摘要:

图像超分辨率重建旨在从低分辨率图像恢复出高分辨率清晰图像。阐述了典型图像超分辨率重建方法的思想,从上采样位置和上采样方法、学习策略、损失函数等维度,对典型和最新的基于深度学习的图像超分辨率重建算法进行了评述,分析了最新的发展现状,并对未来发展趋势进行了展望。

关键词: 图像超分辨率重建, 深度学习, 图像质量评价