Deep learning-based image super-resolution considering quantitative and perceptual quality

Jun Ho Choi; Jun Hyuk Kim; Manri Cheon; Jong Seok Lee

doi:10.1016/j.neucom.2019.06.103

Deep learning-based image super-resolution considering quantitative and perceptual quality

Jun Ho Choi, Jun Hyuk Kim, Manri Cheon, Jong Seok Lee

School of Integrated Technology

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

14 Citations (Scopus)

Abstract

Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the naturalness, respectively. In this paper, we propose a novel super-resolution method that can improve the perceptual quality of the upscaled images while preserving the conventional quantitative performance. The proposed method employs a deep network for multi-pass upscaling in company with a discriminator network and two qualitative score predictor networks. Experimental results demonstrate that the proposed method achieves a good balance of the quantitative and perceptual quality, showing more satisfactory results than existing methods.

Original language	English
Pages (from-to)	347-359
Number of pages	13
Journal	Neurocomputing
Volume	398
DOIs	https://doi.org/10.1016/j.neucom.2019.06.103
Publication status	Published - 2020 Jul 20

Bibliographical note

Funding Information:
This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the “ICT Consilience Creative Program” (IITP-2019-2017-0-01015) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation). In addition, this work was also supported by the IITP grant funded by the Korea government (MSIT) ( R7124-16-0004 , Development of Intelligent Interaction Technology Based on Context Awareness and Human Intention Understanding).

Publisher Copyright:
© 2019 Elsevier B.V.

All Science Journal Classification (ASJC) codes

Computer Science Applications
Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/j.neucom.2019.06.103

Cite this

@article{433a1115f7c14d21affe5439d1bb912c,

title = "Deep learning-based image super-resolution considering quantitative and perceptual quality",

abstract = "Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the naturalness, respectively. In this paper, we propose a novel super-resolution method that can improve the perceptual quality of the upscaled images while preserving the conventional quantitative performance. The proposed method employs a deep network for multi-pass upscaling in company with a discriminator network and two qualitative score predictor networks. Experimental results demonstrate that the proposed method achieves a good balance of the quantitative and perceptual quality, showing more satisfactory results than existing methods.",

author = "Choi, {Jun Ho} and Kim, {Jun Hyuk} and Manri Cheon and Lee, {Jong Seok}",

note = "Funding Information: This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the “ICT Consilience Creative Program” (IITP-2019-2017-0-01015) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation). In addition, this work was also supported by the IITP grant funded by the Korea government (MSIT) ( R7124-16-0004 , Development of Intelligent Interaction Technology Based on Context Awareness and Human Intention Understanding). Publisher Copyright: {\textcopyright} 2019 Elsevier B.V.",

year = "2020",

month = jul,

day = "20",

doi = "10.1016/j.neucom.2019.06.103",

language = "English",

volume = "398",

pages = "347--359",

journal = "Review of Economic Dynamics",

issn = "1094-2025",

publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Deep learning-based image super-resolution considering quantitative and perceptual quality

AU - Choi, Jun Ho

AU - Kim, Jun Hyuk

AU - Cheon, Manri

AU - Lee, Jong Seok

N1 - Funding Information: This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the “ICT Consilience Creative Program” (IITP-2019-2017-0-01015) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation). In addition, this work was also supported by the IITP grant funded by the Korea government (MSIT) ( R7124-16-0004 , Development of Intelligent Interaction Technology Based on Context Awareness and Human Intention Understanding). Publisher Copyright: © 2019 Elsevier B.V.

PY - 2020/7/20

Y1 - 2020/7/20

N2 - Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the naturalness, respectively. In this paper, we propose a novel super-resolution method that can improve the perceptual quality of the upscaled images while preserving the conventional quantitative performance. The proposed method employs a deep network for multi-pass upscaling in company with a discriminator network and two qualitative score predictor networks. Experimental results demonstrate that the proposed method achieves a good balance of the quantitative and perceptual quality, showing more satisfactory results than existing methods.

AB - Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the naturalness, respectively. In this paper, we propose a novel super-resolution method that can improve the perceptual quality of the upscaled images while preserving the conventional quantitative performance. The proposed method employs a deep network for multi-pass upscaling in company with a discriminator network and two qualitative score predictor networks. Experimental results demonstrate that the proposed method achieves a good balance of the quantitative and perceptual quality, showing more satisfactory results than existing methods.

UR - http://www.scopus.com/inward/record.url?scp=85074505918&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074505918&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2019.06.103

DO - 10.1016/j.neucom.2019.06.103

M3 - Article

AN - SCOPUS:85074505918

SN - 1094-2025

VL - 398

SP - 347

EP - 359

JO - Review of Economic Dynamics

JF - Review of Economic Dynamics

ER -

Deep learning-based image super-resolution considering quantitative and perceptual quality

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this