摘要
图像超分辨率重建是计算机视觉中的基本图像处理技术之一,不仅可以提高图像分辨率改善图像质量,还可以辅助其他计算机视觉任务.近年来,随着人工智能浪潮的兴起,基于深度学习的图像超分辨率重建也取得了显著进展.本文在简述图像超分辨率重建方法的基础上,全面综述了基于深度学习的单帧图像超分辨率重建的技术架构及研究历程,包括数据集构建方式、网络模型基本框架以及用于图像质量评估的主、客观评价指标,重点介绍了根据网络结构及图像重建效果划分的基于卷积神经网络的方法、基于生成对抗网络的方法以及基于Transformer的方法,并对相关网络模型加以评述和对比,最后依据网络模型和超分辨率重建挑战赛相关内容,展望了图像超分辨率重建未来的发展趋势.
Image super-resolution reconstruction is one of the basic image processing techniques in computer vision,which can not only improve image resolution and image quality,but also assist other computer vision tasks.In recent years,with the rise of artificial intelligence,deep-learning-based image super-resolution reconstruction has also made remarkable progress.Based on a brief description of the image super-resolution reconstruction methodology,this paper comprehensive⁃ly reviews the technical architecture and research process of deep-learning-based single image super-resolution reconstruc⁃tion,including the method of datasets construction,the basic framework of the network model,the subjective and objective evaluation metrics for image quality evaluation.The methods based on convolutional neural networks,generative adversari⁃al networks and Transformer,which are divided according to network structure and image reconstruction effect are mainly introduced,and related network models are reviewed and compared.Finally,the future development trend of image superresolution reconstruction is prospected according to the related content of network model and super-resolution reconstruc⁃tion challenges.
作者
吴靖
叶晓晶
黄峰
陈丽琼
王志锋
刘文犀
WU Jing;YE Xiao-jing;HUANG Feng;CHEN Li-qiong;WANG Zhi-feng;LIU Wen-xi(School of Mechanical Engineering and Automation,Fuzhou University,Fuzhou,Fujian 350116,China;Advanced Technology Innovation Institute,Fuzhou University,Fuzhou,Fujian 350116,China;College of Computer and Data Science,Fuzhou University,Fuzhou,Fujian 350116,China)
出处
《电子学报》
EI
CAS
CSCD
北大核心
2022年第9期2265-2294,共30页
Acta Electronica Sinica
基金
国家自然科学基金(No.62072110)。
