Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (5): 972-990.DOI: 10.3778/j.issn.1673-9418.2111126

• Surveys and Frontiers • Previous Articles     Next Articles

Review of Super-Resolution Image Reconstruction Algorithms

ZHONG Mengyuan, JIANG Lin()   

  1. Faculty of Science, Kunming University of Science and Technology, Kunming 650093, China
  • Received:2021-11-10 Revised:2022-01-05 Online:2022-05-01 Published:2022-05-19
  • About author:ZHONG Mengyuan, born in 1998, M.S. candidate. Her research interests include image processing and computer vision.
    JIANG Lin, born in 1969, professor. His research interest is intelligent network computing.
  • Supported by:
    National Natural Science Foundation of China(11761042);Foundation of Yunnan Provincial Education Department(KKJB201707008)

超分辨率图像重建算法综述

钟梦圆, 姜麟()   

  1. 昆明理工大学 理学院,昆明 650093
  • 通讯作者: + E-mail: tojianglin@126.com
  • 作者简介:钟梦圆(1998—),女,四川泸州人,硕士研究生,主要研究方向为图像处理、计算机视觉。
    姜麟(1969—),男,湖南益阳人,教授,主要研究方向为智能网络计算。
  • 基金资助:
    国家自然科学基金(11761042);云南省教育厅基金(KKJB201707008)

Abstract:

In human visual perception system, high-resolution (HR) image is an important medium to clearly express its spatial structure, detailed features, edge texture and other information, and it has a very wide range of practical value in medicine, criminal investigation, satellite and other fields. Super-resolution image reconstruction (SRIR) is a key research task in the field of computer vision and image processing, which aims to reconstruct a high-resolution image with clear details from a given low-resolution (LR) image. In this paper, the concept and mathematical model of super-resolution image reconstruction are firstly described, and the image reconstruction methods are systematically classified into three kinds of super-resolution image reconstruction methods:based on interpolation, based on reconstruction, based on learning (before and after deep learning). Secondly, the typical, commonly used and latest algorithms among the three methods and their research are comprehensively reviewed and summarized, and the listed image reconstruction algorithms are combed from the aspects of network structure, learning mechanism, application scenarios, advantages and limitations. Then, the datasets and image quality evaluation indices used for super-resolution image reconstruction algorithms are summarized, and the characteristics and performance of various super-resolution image reconstruction algorithms based on deep learning are compared. Finally, the future research direction or angle of super-resolution image reconstruction is prospected from four aspects.

Key words: image processing, super-resolution reconstruction, deep learning, image quality assessment

摘要:

在人类视觉感知系统中,高分辨率(HR)图像是图像清晰表达其空间结构、细节特征、边缘纹理等信息的重要媒介,在医学、刑侦、卫星等领域有着极为广泛的实用价值。超分辨率图像重建(SRIR)旨在从给定的低分辨率(LR)图像中,重建含有清晰细节特征的高分辨率图像,是计算机视觉和图像处理领域中的一项重点研究任务。首先,对超分辨率图像重建的概念和数学模型进行阐述,并对图像重建方法进行系统分类,将其系统地分为基于插值、基于重构、基于学习(深度学习前、后)三类超分辨率图像重建方法;其次,对三类方法中典型的、常用的、最新的算法及其研究进行全面回顾和综述,并从网络结构、学习机制、适用场景、优势和局限性等方面对所列的图像重建算法进行了梳理;然后,归纳总结了超分辨率图像重建算法所用的数据集和图像质量评价指标,重点比较基于深度学习的各种超分辨率图像重建算法的特点与性能;最后,从四方面对超分辨率图像重建问题未来的研究方向或角度进行展望。

关键词: 图像处理, 超分辨率重建, 深度学习, 图像质量评估

CLC Number: