scholarly journals An Effective Single-Image Super-Resolution Model Using Squeeze-and-Excitation Networks

2018 ◽  
pp. 542-553 ◽  
Author(s):  
Kangfu Mei ◽  
Aiwen Jiang ◽  
Juncheng Li ◽  
Jihua Ye ◽  
Mingwen Wang
Keyword(s):  
Super Resolution ◽  
Single Image ◽  
Resolution Model ◽  
Image Super Resolution ◽  
Single Image Super Resolution

scholarly journals Single Image Super Resolution Model Using Learnable Weight Factor in Residual Skip Connection

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 58676-58684
Author(s):  
Ruaa A. Al-falluji ◽  
Aliaa A. A Youssif ◽  
Shawkat K. Guirguis
Keyword(s):  
Super Resolution ◽  
Weight Factor ◽  
Single Image ◽  
Resolution Model ◽  
Image Super Resolution ◽  
Single Image Super Resolution

Deep fractal residual network for fast and accurate single image super resolution

2020 ◽  
Vol 398 ◽  
pp. 389-398 ◽  
Author(s):  
Yanghao Zhou ◽  
Jianfeng Dong ◽  
Yubin Yang
Keyword(s):  
Super Resolution ◽  
Single Image ◽  
Residual Network ◽  
Image Super Resolution ◽  
Single Image Super Resolution

scholarly journals Real-Time Environment Monitoring Using a Lightweight Image Super-Resolution Network

2021 ◽  
Vol 18 (11) ◽  
pp. 5890
Author(s):  
Qiang Yu ◽  
Feiqiang Liu ◽  
Long Xiao ◽  
Zitao Liu ◽  
Xiaomin Yang
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Super Resolution ◽  
Model Complexity ◽  
Practical Application ◽  
Single Image ◽  
Feature Maps ◽  
Benchmark Datasets ◽  
Image Super Resolution ◽  
Single Image Super Resolution

Deep-learning (DL)-based methods are of growing importance in the field of single image super-resolution (SISR). The practical application of these DL-based models is a remaining problem due to the requirement of heavy computation and huge storage resources. The powerful feature maps of hidden layers in convolutional neural networks (CNN) help the model learn useful information. However, there exists redundancy among feature maps, which can be further exploited. To address these issues, this paper proposes a lightweight efficient feature generating network (EFGN) for SISR by constructing the efficient feature generating block (EFGB). Specifically, the EFGB can conduct plain operations on the original features to produce more feature maps with parameters slightly increasing. With the help of these extra feature maps, the network can extract more useful information from low resolution (LR) images to reconstruct the desired high resolution (HR) images. Experiments conducted on the benchmark datasets demonstrate that the proposed EFGN can outperform other deep-learning based methods in most cases and possess relatively lower model complexity. Additionally, the running time measurement indicates the feasibility of real-time monitoring.

Compact and progressive network for enhanced single image super-resolution—ComPrESRNet

2021 ◽  
Author(s):  
Vishal Chudasama ◽  
Kishor Upla ◽  
Kiran Raja ◽  
Raghavendra Ramachandra ◽  
Christoph Busch
Keyword(s):  
Super Resolution ◽  
Single Image ◽  
Image Super Resolution ◽  
Single Image Super Resolution

scholarly journals Noisy Single Image Super-resolution Based on Local Fractal Feature Analysis

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Kai Shao ◽  
Qinglan Fan ◽  
Yunfeng Zhang ◽  
Fangxun Bao ◽  
Caiming Zhang
Keyword(s):  
Super Resolution ◽  
Feature Analysis ◽  
Single Image ◽  
Image Super Resolution ◽  
Single Image Super Resolution

Kernel-attended residual network for single image super-resolution

2021 ◽  
Vol 213 ◽  
pp. 106663
Author(s):  
Yujie Dun ◽  
Zongyang Da ◽  
Shuai Yang ◽  
Yao Xue ◽  
Xueming Qian
Keyword(s):  
Super Resolution ◽  
Single Image ◽  
Residual Network ◽  
Image Super Resolution ◽  
Single Image Super Resolution
Sign in / Sign up

Export Citation Format

Share Document