基于深度学习的图像超分辨率重建方法浅析  

An Analysis of Image Super-Resolution Reconstruction Method Based on Deep Learning

作　　者：江曙 王俊英[1] 董岱 陈晗晗 任肖月 JIANG Shu;WANG Junying;DONG Dai;CHEN Hanhan;Ren Xiaoyue(College of Computer and Information,Three Gorges University Yichang 443002,China;Heading data intelligence Co.,Ltd,Wuhan 430223,China)

机构地区：[1]三峡大学计算机与信息学院,湖北宜昌443002 [2]武汉中海庭数据技术有限公司,湖北武汉430223

出　　处：《长江信息通信》2022年第12期28-30,34,共4页Changjiang Information & Communications

摘　　要：图像超分辨率是图像处理中一个经典问题,从低分辨率图像中恢复高分辨率图像的不确定性给问题的求解带来了极大的挑战。作为一个热门的应用领域,从问题提出至今,研究者们提出了许多的解决方法。随着科技进步和深度学习的发展,基于卷积神经网络等的深度学习方法应用于图像超分辨率重建,使得重建图像的质量得到了极大的提高。文章对基于深度学习的图像超分辨率重建的一些较为经典的方法进行了总结与探讨,分析了其中的优势与不足,并指出了目前方法中存在的问题和今后研究可以努力的方向。Image super-resolution is a classic problem in image processing,and the uncertainty of recovering high-resolution images from low-resolution images brings great challenges to solving the problem.As a popular application field,researchers have proposed many solutions since the problem was raised.With the advancement of science and technology and the development of deep learning,deep learning methods based on convolutional neural networks are applied to image super-resolution reconstruction,which greatly improves the quality of reconstructed images.This paper summarizes and discusses some of the more classic methods of image super-resolution reconstruction based on deep learning,analyzes the advantages and disadvantages,and points out the problems existing in the current methods and the direction for future research.

关 键 词：深度学习 图像超分辨率重建 卷积神经网络 残差学习 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]