Multi-Perspective Discriminators-Based Generative Adversarial Network for Image Super Resolution
- Authors
- Lee, Oh-Young; Shin, Yoon-Ho; Kim, Jong-Ok
- Issue Date
- 2019
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Generators; Discrete cosine transforms; Deep learning; Generative adversarial networks; Frequency-domain analysis; Spatial resolution; Image super-resolution; deep learning for super resolution; SR GAN; multi-discriminators
- Citation
- IEEE ACCESS, v.7, pp.136496 - 136510
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE ACCESS
- Volume
- 7
- Start Page
- 136496
- End Page
- 136510
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/68952
- DOI
- 10.1109/ACCESS.2019.2942779
- ISSN
- 2169-3536
- Abstract
- Recently, generative adversarial network-based image super resolution has been investigated, and it has been shown to lead to overwhelming improvements in subjective quality. However, it also leads to checkerboard artifacts and the unpleasing high-frequency (HF) components. In this paper, we propose a multi-discriminators-based image super resolution method that distinguishes those artifacts from various perspectives. First, the DCT perspective discriminator is proposed because the checkerboard artifacts are easily separated on the frequency domain. Second, the gradient perspective discriminator is proposed, because the unpleasing HF components can be discriminated on the gradient magnitude distribution. These proposed multi-perspective discriminators can easily identify artifacts, and they can help the generator reproduce artifact-less SR images. The experimental results show that the proposed SR-GAN with multi-perspective discriminators achieves objective and subjective quality improvements in terms of PSNR, SSIM, PI and MOS, as compared to the conventional SR-GAN by reducing the aforementioned artifacts.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.