scholarly journals Adaptive Transform Domain Image Super-Resolution via Orthogonally Regularized Deep Networks

2019 ◽  
Vol 28 (9) ◽  
pp. 4685-4700 ◽  
Author(s):  
Tiantong Guo ◽  
Hojjat Seyed Mousavi ◽  
Vishal Monga
Keyword(s):  
Super Resolution ◽  
Transform Domain ◽  
Deep Networks ◽  
Image Super Resolution ◽  
Adaptive Transform

scholarly journals On Training Deep Networks for Satellite Image Super-Resolution

2019 ◽  
Author(s):  
Michal Kawulok ◽  
Szymon Piechaczek ◽  
Krzysztof Hrynczenko ◽  
Pawel Benecki ◽  
Daniel Kostrzewa ◽  
...  
Keyword(s):  
Satellite Image ◽  
Super Resolution ◽  
Deep Networks ◽  
Image Super Resolution

Lightweight Single Image Super-resolution with Dense Connection Distillation Network

2021 ◽  
Vol 17 (1s) ◽  
pp. 1-17
Author(s):  
Yanchun Li ◽  
Jianglian Cao ◽  
Zhetao Li ◽  
Sangyoon Oh ◽  
Nobuyoshi Komuro
Keyword(s):  
Feature Fusion ◽  
Super Resolution ◽  
Single Image ◽  
Feature Maps ◽  
Deep Networks ◽  
Benchmark Datasets ◽  
Rich Information ◽  
Image Super Resolution ◽  
Single Image Super Resolution ◽  
Training Efficiency

Single image super-resolution attempts to reconstruct a high-resolution (HR) image from its corresponding low-resolution (LR) image, which has been a research hotspot in computer vision and image processing for decades. To improve the accuracy of super-resolution images, many works adopt very deep networks to model the translation from LR to HR, resulting in memory and computation consumption. In this article, we design a lightweight dense connection distillation network by combining the feature fusion units and dense connection distillation blocks (DCDB) that include selective cascading and dense distillation components. The dense connections are used between and within the distillation block, which can provide rich information for image reconstruction by fusing shallow and deep features. In each DCDB, the dense distillation module concatenates the remaining feature maps of all previous layers to extract useful information, the selected features are then assessed by the proposed layer contrast-aware channel attention mechanism, and finally the cascade module aggregates the features. The distillation mechanism helps to reduce training parameters and improve training efficiency, and the layer contrast-aware channel attention further improves the performance of model. The quality and quantity experimental results on several benchmark datasets show the proposed method performs better tradeoff in term of accuracy and efficiency.

Ensemble based deep networks for image super-resolution

2017 ◽  
Vol 68 ◽  
pp. 191-198 ◽  
Author(s):  
Lingfeng Wang ◽  
Zehao Huang ◽  
Yongchao Gong ◽  
Chunhong Pan
Keyword(s):  
Super Resolution ◽  
Deep Networks ◽  
Image Super Resolution
Sign in / Sign up

Export Citation Format

Share Document