BROWSE
Detail
Journal Article
Enhanced Single Image Super Resolution Method Using Lightweight Multi-Scale Channel Dense Network
- Authors
- Yooho Lee, Dongsan Jun, Byung-Gyu Kim, Hunjoo Lee
- Issue Date
- 2021-05
- Citation
- Sensors, v.21, no.10, pp.1-17
- ISSN
- 1424-8220
- Publisher
- MDPI
- Language
- English
- Type
- Journal Article
- Abstract
- 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 multiscale 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.
- KSP Keywords
- Computer Vision(CV), Dense network, High resolution, Multi-scale, Perceptual Quality, Resolution method, Trade-off, image restoration, low-resolution(LR), memory capacity, network complexity
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
