Multi-Perspective Discriminators-Based Generative Adversarial Network for Image Super Resolution

Oh Young Lee; Yoon Ho Shin; Jong Ok Kim

doi:10.1109/ACCESS.2019.2942779

Multi-Perspective Discriminators-Based Generative Adversarial Network for Image Super Resolution

Oh Young Lee, Yoon Ho Shin, Jong Ok Kim

Research output: Contribution to journal › Article › peer-review

18 Citations (Scopus)

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.

Original language	English
Article number	8845591
Pages (from-to)	136496-136510
Number of pages	15
Journal	IEEE Access
Volume	7
DOIs	https://doi.org/10.1109/ACCESS.2019.2942779
Publication status	Published - 2019

Bibliographical note

Funding Information:
This work was supported in part by the National Research Foundation of Korea (NRF) through the Korean Government (MSIT) under Grant 2019R1A2C1005834, and in part by the Ministry of Science and ICT (MSIT), South Korea, through the Information Technology Research Center (ITRC) Support Program supervised by the Institute of Information and Communications Technology Planning and Evaluation (IITP) under Grant IITP-2019-2018-0-01421.

Publisher Copyright:
© 2013 IEEE.

Keywords

Image super-resolution
SR GAN
deep learning for super resolution
multi-discriminators

ASJC Scopus subject areas

General Computer Science
General Materials Science
General Engineering

Access to Document

10.1109/ACCESS.2019.2942779

Cite this

@article{c82eacf5730c424cbb2b647919124176,

title = "Multi-Perspective Discriminators-Based Generative Adversarial Network for Image Super Resolution",

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.",

keywords = "Image super-resolution, SR GAN, deep learning for super resolution, multi-discriminators",

author = "Lee, {Oh Young} and Shin, {Yoon Ho} and Kim, {Jong Ok}",

note = "Funding Information: This work was supported in part by the National Research Foundation of Korea (NRF) through the Korean Government (MSIT) under Grant 2019R1A2C1005834, and in part by the Ministry of Science and ICT (MSIT), South Korea, through the Information Technology Research Center (ITRC) Support Program supervised by the Institute of Information and Communications Technology Planning and Evaluation (IITP) under Grant IITP-2019-2018-0-01421. Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2019",

doi = "10.1109/ACCESS.2019.2942779",

language = "English",

volume = "7",

pages = "136496--136510",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Multi-Perspective Discriminators-Based Generative Adversarial Network for Image Super Resolution

AU - Lee, Oh Young

AU - Shin, Yoon Ho

AU - Kim, Jong Ok

N1 - Funding Information: This work was supported in part by the National Research Foundation of Korea (NRF) through the Korean Government (MSIT) under Grant 2019R1A2C1005834, and in part by the Ministry of Science and ICT (MSIT), South Korea, through the Information Technology Research Center (ITRC) Support Program supervised by the Institute of Information and Communications Technology Planning and Evaluation (IITP) under Grant IITP-2019-2018-0-01421. Publisher Copyright: © 2013 IEEE.

PY - 2019

Y1 - 2019

N2 - 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.

AB - 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.

KW - Image super-resolution

KW - SR GAN

KW - deep learning for super resolution

KW - multi-discriminators

UR - http://www.scopus.com/inward/record.url?scp=85078228188&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2942779

DO - 10.1109/ACCESS.2019.2942779

M3 - Article

AN - SCOPUS:85078228188

SN - 2169-3536

VL - 7

SP - 136496

EP - 136510

JO - IEEE Access

JF - IEEE Access

M1 - 8845591

ER -

Multi-Perspective Discriminators-Based Generative Adversarial Network for Image Super Resolution

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this