Multi-scale channel network based on filer pruning for image super-resolution

Optik ◽  
2021 ◽  
Vol 236 ◽  
pp. 166641
Author(s):  
Deyun Wei ◽  
Zhaowu Wang
2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Wenyi Wang ◽  
Jun Hu ◽  
Xiaohong Liu ◽  
Jiying Zhao ◽  
Jianwen Chen

AbstractIn this paper, we propose a hybrid super-resolution method by combining global and local dictionary training in the sparse domain. In order to present and differentiate the feature mapping in different scales, a global dictionary set is trained in multiple structure scales, and a non-linear function is used to choose the appropriate dictionary to initially reconstruct the HR image. In addition, we introduce the Gaussian blur to the LR images to eliminate a widely used but inappropriate assumption that the low resolution (LR) images are generated by bicubic interpolation from high-resolution (HR) images. In order to deal with Gaussian blur, a local dictionary is generated and iteratively updated by K-means principal component analysis (K-PCA) and gradient decent (GD) to model the blur effect during the down-sampling. Compared with the state-of-the-art SR algorithms, the experimental results reveal that the proposed method can produce sharper boundaries and suppress undesired artifacts with the present of Gaussian blur. It implies that our method could be more effect in real applications and that the HR-LR mapping relation is more complicated than bicubic interpolation.


2017 ◽  
Vol 76 (23) ◽  
pp. 24871-24902 ◽  
Author(s):  
Xiaomin Yang ◽  
Wei Wu ◽  
Kai Liu ◽  
Weilong Chen ◽  
Ping Zhang ◽  
...  

2020 ◽  
Vol 57 (16) ◽  
pp. 161012
Author(s):  
徐志刚 Xu Zhigang ◽  
闫娟娟 Yan Juanjuan ◽  
朱红蕾 Zhu Honglei

2020 ◽  
pp. 1-11
Author(s):  
Jin Wan ◽  
Hui Yin ◽  
Zhihao Liu ◽  
Aixin Chong ◽  
Yanting Liu

Author(s):  
Juncheng Li ◽  
Faming Fang ◽  
Jiaqian Li ◽  
Kangfu Mei ◽  
Guixu Zhang

Sign in / Sign up

Export Citation Format

Share Document