深度学习的图像超分辨率重建技术综述  

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

作　　者：杨才东 李承阳 李忠博 谢永强 孙方伟 齐锦 YANG Caidong;LI Chengyang;LI Zhongbo;XIE Yongqiang;SUN Fangwei;QI Jin(Institute of Systems Engineering,Academy of Military Sciences,Beijing 100141,China;School of Electronics Engineering and Computer Science,Peking University,Beijing 100871,China)

机构地区：[1]军事科学院系统工程研究院,北京100141 [2]北京大学信息科学与技术学院,北京100871

出　　处：《计算机科学与探索》2022年第9期1990-2010,共21页Journal of Frontiers of Computer Science and Technology

摘　　要：图像超分辨率重建技术的本质是突破现有硬件条件的限制,通过算法将低分辨率图像重建为高分辨率图像,获得包含更多信息的图像的技术。随着深度学习理论和技术的迅速发展,深度学习被引入到超分辨率重建领域并取得了进展。对基于深度学习的图像超分辨率重建算法进行了全面总结,并对已有算法进行了分类、分析和比较。首先,详细介绍了单图像超分辨率重建模型的组成结构,包括超分框架、上采样方法、非线性映射学习模块以及损失函数等。其次,从图像对齐和Patch匹配两方面出发,对现有的基于参考的图像超分辨率重建算法进行了分析。然后,介绍了图像超分辨重建领域的benchmark数据集以及图像质量评估参数,对目前主流算法的性能进行了评估。最后,对基于深度学习的图像超分辨率重建算法的未来研究趋势进行了展望。The essence of image super-resolution reconstruction technology is to break through the limitation of hardware conditions, and reconstruct a high-resolution image from a low-resolution image which contains less information through the image super-resolution reconstruction algorithms. With the development of the technology on deep learning, deep learning has been introduced into the image super-resolution reconstruction field. This paper summarizes the image super-resolution reconstruction algorithms based on deep learning, classifies, analyzes and compares the typical algorithms. Firstly, the model framework, upsampling method, nonlinear mapping learning module and loss function of single image super-resolution reconstruction method are introduced in detail. Secondly,the reference-based super-resolution reconstruction method is analyzed from two aspects: pixel alignment and Patch matching. Then, the benchmark datasets and image quality evaluation indices used for image super-resolution reconstruction algorithms are summarized, the characteristics and performance of the typical super-resolution reconstruction algorithms are compared and analyzed. Finally, the future research trend on the image super-resolution reconstruction algorithms based on deep learning is prospected.

关 键 词：超分辨率重建 深度学习 单图像 基于参考 图像对齐 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]