轻量级图像超分辨率研究综述  

Review of Research on Lightweight Image Super-Resolution

作　　者：朱新峰[1] 宋健 ZHU Xinfeng;SONG Jian(School of Information Engineering,Yangzhou University,Yangzhou,Jiangsu 225000,China)

机构地区：[1]扬州大学信息工程学院,江苏扬州225000

出　　处：《计算机工程与应用》2024年第16期49-60,共12页Computer Engineering and Applications

基　　金：国家自然科学基金(62073283)。

摘　　要：基于深度学习的图像超分辨率(super-resolution,SR)受到广泛关注,其目的是提高图像的分辨率,以便对图像做进一步的处理,如目标检测、图像分类和人脸识别等。图像SR领域相关研究近年来取得了迅猛发展,但有关轻量级SR模型的相关综述还不多见。对基于深度学习的轻量级SR方法研究现状和损失函数进行了分析,并对目前轻量级SR方法进行了新的分类,分别为传统卷积方法和注意力机制方法。系统梳理了图像轻量级SR方法的发展历程和最新进展,指出了每一种方法存在的优势和缺陷。最后对当前轻量级SR技术存在的问题进行了分析,并给出了轻量级图像SR方法未来的研究方向。In recent years,image super-resolution(SR)based on deep learning has received widespread attention.The purpose of image SR is to improve the resolution of images to facilitate further processing of images,such as target detection,image classification and face recognition,etc.The research on image SR has achieved rapid development in recent years,but there are still few related reviews on lightweight SR models.By analyzing the current research status of lightweight SR methods which are based on deep learning and loss function,a new classification of current lightweight SR models is made,which are traditional convolution methods and attention mechanism methods.The development history and latest progress of lightweight SR methods for images are systematically given,the advantages and disadvantages of each method are pointed out.Finally,by analyzing the existing problems of current lightweight SR technology,the future research directions of lightweight image SR method are given.

关 键 词：图像超分辨率 轻量级 深度学习 卷积神经网络 注意力机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]