基于深度学习的单幅图像超分辨率重建算法综述  

A Review of Single Image Super-resolution Reconstruction Algorithms Based on Deep Learning

作　　者：李佳星 赵勇先 王京华 LI Jia-Xing;ZHAO Yong-Xian;WANG Jing-Hua(College of Mechanical and Electric Engineering,Changchun University of Science and Technology,Changchun 130022;Cha-ngchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033;University of Chinese Academy of Sciences,Beijing 100049;Ministry of Education Key Laboratory for Cross-Scale Micro and Nano Man-ufacturing,Changchun University of Science and Technology,Changchun 130022)

机构地区：[1]长春理工大学机电工程学院,长春130022 [2]中国科学院长春光学精密机械与物理研究所,长春130033 [3]中国科学院大学,北京100049 [4]长春理工大学跨尺度微纳制造教育部重点实验室,长春130022

出　　处：《自动化学报》2021年第10期2341-2363,共23页Acta Automatica Sinica

基　　金：国防基础科研计划(JCKY2019411B001);“111”计划(D17017);露泉创新基金(LQ-2020-01)资助。

摘　　要：单幅图像超分辨率(Single image super-resolution,SISR)重建是计算机视觉领域上的一个重要问题,在安防视频监控、飞机航拍以及卫星遥感等方面具有重要的研究意义和应用价值.近年来,深度学习在图像分类、检测、识别等诸多领域中取得了突破性进展,也推动着图像超分辨率重建技术的发展.本文首先介绍单幅图像超分辨率重建的常用公共图像数据集;然后,重点阐述基于深度学习的单幅图像超分辨率重建方向的创新与进展;最后,讨论了单幅图像超分辨率重建方向上存在的困难和挑战,并对未来的发展趋势进行了思考与展望.Single image super-resolution(SISR)reconstruction is an important problem in the field of computer vision.It has important research significance and application value in security video surveillance,aircraft aerial photography and satellite remote sensing.In recent years,deep learning has made a breakthrough in many fields such as image classification,detection and recognition,and promoted the development of image super-resolution reconstruction technology.This paper first introduces the common public image datasets for single image super-resolution reconstruction.Then,the innovation and progress of single image super-resolution reconstruction based on deep learning are emphasized.Finally,the difficulties and challenges in the single image super-resolution reconstruction are discussed,and the future development trend is discussed.

关 键 词：单幅图像超分辨率 计算机视觉 深度学习 神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]