A Single Image Super-Resolution Reconstruction Based on Fusion

被引:1
作者
Su Jin-sheng [1 ]
Zhang Ming-jun [1 ]
Yu Wen-jing [1 ]
机构
[1] Software Engn Inst Guangzhou, Dept Network Technol, Guangzhou 510990, Peoples R China
来源
THIRTEENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2021) | 2022年 / 12083卷
关键词
super-resolution reconstruction; image fusion; generative adversarial networks; NETWORK;
D O I
10.1117/12.2623592
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Image super-resolution is to restore a high-resolution image from a low-resolution image or image sequence. High resolution means that the image has a high pixel density and can provide more details, which often play a key role in the application. Aiming at the application of single-frame low-resolution reconstruction and super-resolution, this paper proposes a method based on image fusion. This method combines two or more methods of super-resolution image reconstruction using generative adversarial neural networks. The reconstructed images are fused. Image fusion uses the integration of two or more images into a new image. Fusion can make use of the temporal and spatial correlation and information complementarity of two or more images, which can make the image obtained after fusion have a more comprehensive and clear description of the scene, which is more conducive to human eye recognition. This paper draws on the idea of ensemble learning, and uses the super-resolution images generated by the three super-resolution reconstruction algorithms of BasicSR, SRGAN and ESRGAN to carry out two-by-two cross fusion for simulation experiments. The experimental results show that this kind of reconstruction using different generation adversarial networks to generate the super-resolution image by fusion is simple and effective. The super-resolution image quality after fusion is generally better than the image quality before fusion in terms of PSNR and SSIM.
引用
收藏
页数:7
相关论文
共 23 条
[1]   Enhancing Image Quality via Style Transfer for Single Image Super-Resolution [J].
Deng, Xin .
IEEE SIGNAL PROCESSING LETTERS, 2018, 25 (04) :571-575
[2]   Image Super-Resolution Using Deep Convolutional Networks [J].
Dong, Chao ;
Loy, Chen Change ;
He, Kaiming ;
Tang, Xiaoou .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (02) :295-307
[3]   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
[4]  
Fan W, 2007, PROC CVPR IEEE, P244
[5]   Example-based super-resolution [J].
Freeman, WT ;
Jones, TR ;
Pasztor, EC .
IEEE COMPUTER GRAPHICS AND APPLICATIONS, 2002, 22 (02) :56-65
[6]  
Goodfellow I., 2014, ADV NEUR IN, V27, P2672, DOI DOI 10.1145/3422622
[7]   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
[8]   Fast and Accurate Single Image Super-Resolution via Information Distillation Network [J].
Hui, Zheng ;
Wang, Xiumei ;
Gao, Xinbo .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :723-731
[9]   Perceptual Losses for Real-Time Style Transfer and Super-Resolution [J].
Johnson, Justin ;
Alahi, Alexandre ;
Li Fei-Fei .
COMPUTER VISION - ECCV 2016, PT II, 2016, 9906 :694-711
[10]  
Kim J, 2016, PROC CVPR IEEE, P1637, DOI [10.1109/CVPR.2016.181, 10.1109/CVPR.2016.182]