Deep residual network with enhanced upscaling module for super-resolution

Jun Hyuk Kim; Jong Seok Lee

doi:10.1109/CVPRW.2018.00124

Deep residual network with enhanced upscaling module for super-resolution

Jun Hyuk Kim, Jong Seok Lee

School of Integrated Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

45 Citations (Scopus)

Abstract

Single image super-resolution (SR) have recently shown great performance thanks to the advances in deep learning. In the middle of the deep networks for SR, a part that increases image resolution is required, for which a subpixel convolution layer is known as an efficient way. However, we argue that the method has room for improvement, and propose an enhanced upscaling module (EUM), which achieves improvement by utilizing nonlinear operations and skip connections. Employing our proposed EUM, we propose a novel deep residual network for SR, called EUSR. Our proposed EUSR was ranked in the 9th place among 24 teams in terms of SSIM in track 1 of the NTIRE 2018 SR Challenge [25]. In addition, we experimentally show that EUSR has comparable performance on ×2 and ×4 SR for four benchmark datasets to the state-of-the-art methods, and outperforms them on a large scaling factor (x8).

Original language	English
Title of host publication	Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
Publisher	IEEE Computer Society
Pages	913-921
Number of pages	9
ISBN (Electronic)	9781538661000
DOIs	https://doi.org/10.1109/CVPRW.2018.00124
Publication status	Published - 2018 Dec 13
Event	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 - Salt Lake City, United States Duration: 2018 Jun 18 → 2018 Jun 22

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2018-June
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Other

Other	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
Country/Territory	United States
City	Salt Lake City
Period	18/6/18 → 18/6/22

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CVPRW.2018.00124

Cite this

Kim, J. H., & Lee, J. S. (2018). Deep residual network with enhanced upscaling module for super-resolution. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 (pp. 913-921). Article 8575276 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2018.00124

@inproceedings{513d9efe21444984be60832068c59e86,

title = "Deep residual network with enhanced upscaling module for super-resolution",

abstract = "Single image super-resolution (SR) have recently shown great performance thanks to the advances in deep learning. In the middle of the deep networks for SR, a part that increases image resolution is required, for which a subpixel convolution layer is known as an efficient way. However, we argue that the method has room for improvement, and propose an enhanced upscaling module (EUM), which achieves improvement by utilizing nonlinear operations and skip connections. Employing our proposed EUM, we propose a novel deep residual network for SR, called EUSR. Our proposed EUSR was ranked in the 9th place among 24 teams in terms of SSIM in track 1 of the NTIRE 2018 SR Challenge [25]. In addition, we experimentally show that EUSR has comparable performance on ×2 and ×4 SR for four benchmark datasets to the state-of-the-art methods, and outperforms them on a large scaling factor (x8).",

author = "Kim, {Jun Hyuk} and Lee, {Jong Seok}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 ; Conference date: 18-06-2018 Through 22-06-2018",

year = "2018",

month = dec,

day = "13",

doi = "10.1109/CVPRW.2018.00124",

language = "English",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "913--921",

booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018",

address = "United States",

}

Kim, JH & Lee, JS 2018, Deep residual network with enhanced upscaling module for super-resolution. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018., 8575276, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2018-June, IEEE Computer Society, pp. 913-921, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018, Salt Lake City, United States, 18/6/18. https://doi.org/10.1109/CVPRW.2018.00124

Deep residual network with enhanced upscaling module for super-resolution. / Kim, Jun Hyuk; Lee, Jong Seok.
Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society, 2018. p. 913-921 8575276 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Deep residual network with enhanced upscaling module for super-resolution

AU - Kim, Jun Hyuk

AU - Lee, Jong Seok

PY - 2018/12/13

Y1 - 2018/12/13

N2 - Single image super-resolution (SR) have recently shown great performance thanks to the advances in deep learning. In the middle of the deep networks for SR, a part that increases image resolution is required, for which a subpixel convolution layer is known as an efficient way. However, we argue that the method has room for improvement, and propose an enhanced upscaling module (EUM), which achieves improvement by utilizing nonlinear operations and skip connections. Employing our proposed EUM, we propose a novel deep residual network for SR, called EUSR. Our proposed EUSR was ranked in the 9th place among 24 teams in terms of SSIM in track 1 of the NTIRE 2018 SR Challenge [25]. In addition, we experimentally show that EUSR has comparable performance on ×2 and ×4 SR for four benchmark datasets to the state-of-the-art methods, and outperforms them on a large scaling factor (x8).

AB - Single image super-resolution (SR) have recently shown great performance thanks to the advances in deep learning. In the middle of the deep networks for SR, a part that increases image resolution is required, for which a subpixel convolution layer is known as an efficient way. However, we argue that the method has room for improvement, and propose an enhanced upscaling module (EUM), which achieves improvement by utilizing nonlinear operations and skip connections. Employing our proposed EUM, we propose a novel deep residual network for SR, called EUSR. Our proposed EUSR was ranked in the 9th place among 24 teams in terms of SSIM in track 1 of the NTIRE 2018 SR Challenge [25]. In addition, we experimentally show that EUSR has comparable performance on ×2 and ×4 SR for four benchmark datasets to the state-of-the-art methods, and outperforms them on a large scaling factor (x8).

UR - http://www.scopus.com/inward/record.url?scp=85060877241&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060877241&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2018.00124

DO - 10.1109/CVPRW.2018.00124

M3 - Conference contribution

AN - SCOPUS:85060877241

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 913

EP - 921

BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018

PB - IEEE Computer Society

T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018

Y2 - 18 June 2018 through 22 June 2018

ER -

Deep residual network with enhanced upscaling module for super-resolution

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this