Loading...
Please wait, while we are loading the content...
Similar Documents
Enhanced Single Image Super Resolution Method Using Lightweight Multi-Scale Channel Dense Network
| Content Provider | MDPI |
|---|---|
| Author | Lee, Yooho Jun, Dongsan Kim, Byung-Gyu Lee, Hunjoo |
| Copyright Year | 2021 |
| Description | Super resolution (SR) enables to generate a high-resolution (HR) image from one or more low-resolution (LR) images. Since a variety of CNN models have been recently studied in the areas of computer vision, these approaches have been combined with SR in order to provide higher image restoration. In this paper, we propose a lightweight CNN-based SR method, named multi-scale channel dense network (MCDN). In order to design the proposed network, we extracted the training images from the DIVerse 2K (DIV2K) dataset and investigated the trade-off between the SR accuracy and the network complexity. The experimental results show that the proposed method can significantly reduce the network complexity, such as the number of network parameters and total memory capacity, while maintaining slightly better or similar perceptual quality compared to the previous methods. |
| Starting Page | 3351 |
| e-ISSN | 14248220 |
| DOI | 10.3390/s21103351 |
| Journal | Sensors |
| Issue Number | 10 |
| Volume Number | 21 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2021-05-12 |
| Access Restriction | Open |
| Subject Keyword | Sensors Industrial Engineering Deep Learning Super Resolution Convolutional Neural Network Lightweight Neural Network |
| Content Type | Text |
| Resource Type | Article |
