Image super-resolution using supervised multi-scale feature extraction network

2020 ◽  
Author(s):  
Yemei Sun ◽  
Yan Zhang ◽  
Shudong Liu ◽  
Weijia Lu ◽  
Xianguo Li
Keyword(s):  
Feature Extraction ◽  
Super Resolution ◽  
Scale Feature ◽  
Multi Scale ◽  
Image Super Resolution

Multi-scale feature aggregation network for Image super-resolution

2021 ◽  
Author(s):  
Wenlong Chen ◽  
Pengcheng Yao ◽  
Shaoyan Gai ◽  
Feipeng Da
Keyword(s):  
Super Resolution ◽  
Scale Feature ◽  
Multi Scale ◽  
Feature Aggregation ◽  
Image Super Resolution

Compressed multi-scale feature fusion network for single image super-resolution

2018 ◽  
Vol 146 ◽  
pp. 50-60 ◽  
Author(s):  
Xinxia Fan ◽  
Yanhua Yang ◽  
Cheng Deng ◽  
Jie Xu ◽  
Xinbo Gao
Keyword(s):  
Feature Fusion ◽  
Super Resolution ◽  
Single Image ◽  
Scale Feature ◽  
Multi Scale ◽  
Image Super Resolution ◽  
Single Image Super Resolution

scholarly journals Remote Sensing Imagery Super Resolution Based on Adaptive Multi-Scale Feature Fusion Network

Sensors ◽  
2020 ◽  
Vol 20 (4) ◽  
pp. 1142
Author(s):  
Xinying Wang ◽  
Yingdan Wu ◽  
Yang Ming ◽  
Hui Lv
Keyword(s):  
Remote Sensing ◽  
Feature Extraction ◽  
Feature Fusion ◽  
Super Resolution ◽  
Convolutional Network ◽  
Remote Sensing Imagery ◽  
Resolution Image ◽  
Scale Feature ◽  
Multi Scale ◽  
Key Characteristics

Due to increasingly complex factors of image degradation, inferring high-frequency details of remote sensing imagery is more difficult compared to ordinary digital photos. This paper proposes an adaptive multi-scale feature fusion network (AMFFN) for remote sensing image super-resolution. Firstly, the features are extracted from the original low-resolution image. Then several adaptive multi-scale feature extraction (AMFE) modules, the squeeze-and-excited and adaptive gating mechanisms are adopted for feature extraction and fusion. Finally, the sub-pixel convolution method is used to reconstruct the high-resolution image. Experiments are performed on three datasets, the key characteristics, such as the number of AMFEs and the gating connection way are studied, and super-resolution of remote sensing imagery of different scale factors are qualitatively and quantitatively analyzed. The results show that our method outperforms the classic methods, such as Super-Resolution Convolutional Neural Network(SRCNN), Efficient Sub-Pixel Convolutional Network (ESPCN), and multi-scale residual CNN(MSRN).

Sign in / Sign up

Export Citation Format

Share Document