《计算机应用研究》|Application Research of Computers

基于深度学习的单图像超分辨率重建研究综述

Survey of single image super resolution based on deep learning

免费全文下载 (已被下载 次)  
获取PDF全文
作者 南方哲,钱育蓉,行艳妮,赵京霞
机构 新疆大学 软件学院,乌鲁木齐 830046
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)02-001-0321-06
DOI 10.19734/j.issn.1001-3695.2018.10.0610
摘要 为深入了解基于深度学习的单图像超分辨率重建(SISR)的发展,把握当前研究的热点和方向,针对现有基于深度学习的单图像超分辨率重建模型进行了梳理。介绍了相关深度学习算法和基于深度学习的模型以及评价指标,并通过实验对比分析现有模型的性能,其目的在于从本质上了解基于深度学习的单图像超分辨率重建模型的优势;对单图像超分辨率重建的关键问题进行了总结,并对未来的发展趋势进行了展望。
关键词 单图像超分辨率重建; 深度学习; 密集卷积网络; 生成式对抗网络
基金项目 国家自然科学基金资助项目(61562086,61462079,61966035)
新疆维吾尔自治区教育厅创新团队项目(XJEDU2016S035)
自治区研究生创新项目(XJ2019G069,XJ2019G072,XJ2019G071)
本文URL http://www.arocmag.com/article/01-2020-02-001.html
英文标题 Survey of single image super resolution based on deep learning
作者英文名 Nan Fangzhe, Qian Yurong, Xing Yanni, Zhao Jingxia
机构英文名 College of Software,Xinjiang University,Urumqi 830046,China
英文摘要 In order to understand the development of SISR based on deep learning and grasp the hotspots and directions of the current research, this paper combed the existing model of SISR based on deep learning. Firstly, the paper introduced the related deep learning algorithm, these models based on deep learning and their evaluation index. In addition, it compared the performance of existing models through experiments, which aimed to understand the advantages of SISR model based on deep learning. Finally, the paper summarized the key issues of SISR, and prospected the future development trends.
英文关键词 single image super-resolution reconstruction(SISR); deep learning(DL); DenseNet; generative adversarial networks
参考文献 查看稿件参考文献
 
收稿日期 2018/10/31
修回日期 2018/11/23
页码 321-326
中图分类号 TP391
文献标志码 A