NTIRE 2018 challenge on single image super-resolution: Methods and results

Radu Timofte, Shuhang Gu, Luc Van Gool, Lei Zhang, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

31 Citations (Scopus)

Abstract

This paper reviews the 2nd NTIRE challenge on single image super-resolution (restoration of rich details in a low resolution image) with focus on proposed solutions and results. The challenge had 4 tracks. Track 1 employed the standard bicubic downscaling setup, while Tracks 2, 3 and 4 had realistic unknown downgrading operators simulating camera image acquisition pipeline. The operators were learnable through provided pairs of low and high resolution train images. The tracks had 145, 114, 101, and 113 registered participants, resp., and 31 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
PublisherIEEE Computer Society
Pages965-976
Number of pages12
ISBN (Electronic)9781538661000
DOIs
Publication statusPublished - 2018 Dec 13
Event31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 - Salt Lake City, United States
Duration: 2018 Jun 182018 Jun 22

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2018-June
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Other

Other31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
CountryUnited States
CitySalt Lake City
Period18/6/1818/6/22

Fingerprint

Image acquisition
Optical resolving power
Image resolution
Restoration
Gages
Pipelines
Cameras
Testing

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Timofte, R., Gu, S., Van Gool, L., Zhang, L., & Yang, M. H. (2018). NTIRE 2018 challenge on single image super-resolution: Methods and results. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 (pp. 965-976). [8575282] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2018.00130
Timofte, Radu ; Gu, Shuhang ; Van Gool, Luc ; Zhang, Lei ; Yang, Ming Hsuan. / NTIRE 2018 challenge on single image super-resolution : Methods and results. Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society, 2018. pp. 965-976 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).
@inproceedings{35c2eeea5472465f9503ee5cd1872cbe,
title = "NTIRE 2018 challenge on single image super-resolution: Methods and results",
abstract = "This paper reviews the 2nd NTIRE challenge on single image super-resolution (restoration of rich details in a low resolution image) with focus on proposed solutions and results. The challenge had 4 tracks. Track 1 employed the standard bicubic downscaling setup, while Tracks 2, 3 and 4 had realistic unknown downgrading operators simulating camera image acquisition pipeline. The operators were learnable through provided pairs of low and high resolution train images. The tracks had 145, 114, 101, and 113 registered participants, resp., and 31 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.",
author = "Radu Timofte and Shuhang Gu and {Van Gool}, Luc and Lei Zhang and Yang, {Ming Hsuan}",
year = "2018",
month = "12",
day = "13",
doi = "10.1109/CVPRW.2018.00130",
language = "English",
series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",
publisher = "IEEE Computer Society",
pages = "965--976",
booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018",
address = "United States",

}

Timofte, R, Gu, S, Van Gool, L, Zhang, L & Yang, MH 2018, NTIRE 2018 challenge on single image super-resolution: Methods and results. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018., 8575282, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2018-June, IEEE Computer Society, pp. 965-976, 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.2018.00130

NTIRE 2018 challenge on single image super-resolution : Methods and results. / Timofte, Radu; Gu, Shuhang; Van Gool, Luc; Zhang, Lei; Yang, Ming Hsuan.

Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society, 2018. p. 965-976 8575282 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - NTIRE 2018 challenge on single image super-resolution

T2 - Methods and results

AU - Timofte, Radu

AU - Gu, Shuhang

AU - Van Gool, Luc

AU - Zhang, Lei

AU - Yang, Ming Hsuan

PY - 2018/12/13

Y1 - 2018/12/13

N2 - This paper reviews the 2nd NTIRE challenge on single image super-resolution (restoration of rich details in a low resolution image) with focus on proposed solutions and results. The challenge had 4 tracks. Track 1 employed the standard bicubic downscaling setup, while Tracks 2, 3 and 4 had realistic unknown downgrading operators simulating camera image acquisition pipeline. The operators were learnable through provided pairs of low and high resolution train images. The tracks had 145, 114, 101, and 113 registered participants, resp., and 31 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.

AB - This paper reviews the 2nd NTIRE challenge on single image super-resolution (restoration of rich details in a low resolution image) with focus on proposed solutions and results. The challenge had 4 tracks. Track 1 employed the standard bicubic downscaling setup, while Tracks 2, 3 and 4 had realistic unknown downgrading operators simulating camera image acquisition pipeline. The operators were learnable through provided pairs of low and high resolution train images. The tracks had 145, 114, 101, and 113 registered participants, resp., and 31 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.

UR - http://www.scopus.com/inward/record.url?scp=85060865838&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060865838&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2018.00130

DO - 10.1109/CVPRW.2018.00130

M3 - Conference contribution

AN - SCOPUS:85060865838

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

SP - 965

EP - 976

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

PB - IEEE Computer Society

ER -

Timofte R, Gu S, Van Gool L, Zhang L, Yang MH. NTIRE 2018 challenge on single image super-resolution: Methods and results. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society. 2018. p. 965-976. 8575282. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). https://doi.org/10.1109/CVPRW.2018.00130