Overview of Research on Image Super-Resolution Reconstruction

被引：7

作者：

Yu Mengbei ^{[1
]}

Wang Hongjuan ^{[2
]}

Liu Mengyang ^{[1
]}

Li Pei ^{[1
]}

机构：

[1] Beijing Inst Graph Commun, Sch Informat Engn, Beijing, Peoples R China

[2] Beijing Inst Graph Commun, Sch New Media, Beijing, Peoples R China

来源：

2021 IEEE INTERNATIONAL CONFERENCE ON INFORMATION COMMUNICATION AND SOFTWARE ENGINEERING (ICICSE 2021) | 2021年

关键词：

super-resolution; deep learning; neural network structure; image reconstruction;

D O I：

10.1109/ICICSE52190.2021.9404113

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Image super-resolution reconstruction refers to reconstructing a high-resolution image from a low-resolution image through a corresponding method, that is, to generate a clearer image. Throughout the development of this technology, we can see the results of previous efforts, such as image super-resolution reconstruction based on interpolation, image super-resolution reconstruction based on reconstruction, super-resolution reconstruction based on learning, and image super-resolution reconstruction technology based on deep learning. Nowadays, the idea of deep learning is very popular. It is an important branch of machine learning and is widely concerned and favored by researchers. Combining deep learning ideas into the research of image super-resolution reconstruction can achieve very satisfying effects. In this paper, we mainly describe various algorithms of image super-resolution reconstruction based on deep learning, compare their advantages and disadvantages, and discuss their future development directions.

引用

页码：131 / 135

页数：5

共 13 条

[1] Accelerating the Super-Resolution Convolutional Neural Network [J].

Dong, Chao ;

Loy, Chen Change ;

Tang, Xiaoou .

COMPUTER VISION - ECCV 2016, PT II, 2016, 9906 :391-407

[2] Learning a Deep Convolutional Network for Image Super-Resolution [J].

Dong, Chao ;

Loy, Chen Change ;

He, Kaiming ;

Tang, Xiaoou .

COMPUTER VISION - ECCV 2014, PT IV, 2014, 8692 :184-199

[3] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[4]

Irani M., 1990, Proceedings. 10th International Conference on Pattern Recognition (Cat. No.90CH2898-5), P115, DOI 10.1109/ICPR.1990.119340

[5]

Jia Z, 2011, 2011 FIRST ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR), P179, DOI 10.1109/ACPR.2011.6166702

[6]

Kim J., 2015, PROC CVPR IEEE, P1637

[7]

Kim J, 2016, PROC CVPR IEEE, P1637, DOI [10.1109/CVPR.2016.182, 10.1109/CVPR.2016.181]

[8] Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network [J].

Shi, Wenzhe ;

Caballero, Jose ;

Huszar, Ferenc ;

Totz, Johannes ;

Aitken, Andrew P. ;

Bishop, Rob ;

Rueckert, Daniel ;

Wang, Zehan .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :1874-1883

[9] HIGH-RESOLUTION IMAGE RECOVERY FROM IMAGE-PLANE ARRAYS, USING CONVEX PROJECTIONS [J].

STARK, H ;

OSKOUI, P .

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1989, 6 (11) :1715-1726

[10] Image Super-Resolution via Deep Recursive Residual Network [J].

Tai, Ying ;

Yang, Jian ;

Liu, Xiaoming .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :2790-2798

← 1 2 →