AIM 2019 challenge on image extreme super-resolution: Methods and results

Shuhang Gu; Hanwen Liu; Dan Zhu; Tangxin Xie; Xin Yang; Chen Zhu; Jia Yu; Wenyu Sun; Xin Tao; Zijun Deng; Liying Lu; Martin Danelljan; Wenbo Li; Taian Guo; Xiaoyong Shen; Xuemiao Xu; Yu Wing Tai; Jiaya Jia; Peng Yi; Zhongyuan Wang; Kui Jiang; Junjun Jiang; Radu Timofte; Jiayi Ma; Zhi Song Liu; Li Wen Wang; Chu Tak Li; Wan Chi Siu; Yui Lam Chan; Ruofan Zhou; Majed Ei Helou; Kuldeep Purohit; Praveen Kandula; Muhammad Haris; Maitreya Suin; A. Rajagopalan; Kazutoshi Akita; Greg Shakhnarovic; Norimichi Ukita; Pablo Navarrete Michelini; Wenbin Chen

doi:10.1109/ICCVW.2019.00440

AIM 2019 challenge on image extreme super-resolution: Methods and results

Shuhang Gu
, Hanwen Liu
, Dan Zhu
, Tangxin Xie
, Xin Yang
, Chen Zhu
, Jia Yu
, Wenyu Sun
, Xin Tao
, Zijun Deng
, Liying Lu
, Martin Danelljan
, Wenbo Li
, Taian Guo
, Xiaoyong Shen
, Xuemiao Xu
, Yu Wing Tai
, Jiaya Jia
, Peng Yi
, Zhongyuan Wang

Kui Jiang, Junjun Jiang, Radu Timofte, Jiayi Ma, Zhi Song Liu, Li Wen Wang, Chu Tak Li, Wan Chi Siu, Yui Lam Chan, Ruofan Zhou, Majed Ei Helou, Kuldeep Purohit, Praveen Kandula, Muhammad Haris, Maitreya Suin, A. Rajagopalan, Kazutoshi Akita, Greg Shakhnarovic, Norimichi Ukita, Pablo Navarrete Michelini, Wenbin Chen

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

25 Citations (Scopus)

Abstract

This paper reviews the AIM 2019 challenge on extreme image super-resolution, the problem of restoring of rich details in a low resolution image. Compared to previous, this challenge focuses on an extreme upscaling factor, ×16, and employs the novel DIVerse 8K resolution (DIV8K) dataset. This report focuses on the proposed solutions and final results. The challenge had 2 tracks. The goal in Track 1 was to generate a super-resolution result with high fidelity, using the conventional PSNR as the primary metric to evaluate different methods. Track 2 instead focused on generating visually more pleasant super-resolution results, evaluated using subjective opinions. The two tracks had 71 and 52 registered participants, respectively, and 9 teams competed in the final testing phase. This report gauges the experimental protocol and baselines for the extreme image super-resolution task.

Original language	English
Title of host publication	Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3556-3564
Number of pages	9
ISBN (Electronic)	9781728150239
DOIs	https://doi.org/10.1109/ICCVW.2019.00440
Publication status	Published - 27 Oct 2019
Event	17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of Duration: 27 Oct 2019 → 28 Oct 2019

Publication series

Name	Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

Conference

Conference	17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
Country/Territory	Korea, Republic of
City	Seoul
Period	27/10/19 → 28/10/19

Keywords

Extreme super resolution

ASJC Scopus subject areas

Computer Science Applications
Computer Vision and Pattern Recognition

More information

10.1109/ICCVW.2019.00440

http://hdl.handle.net/10397/107158

Cite this

Gu, S., Liu, H., Zhu, D., Xie, T., Yang, X., Zhu, C., Yu, J., Sun, W., Tao, X., Deng, Z., Lu, L., Danelljan, M., Li, W., Guo, T., Shen, X., Xu, X., Tai, Y. W., Jia, J., Yi, P., ... Chen, W. (2019). AIM 2019 challenge on image extreme super-resolution: Methods and results. In Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019 (pp. 3556-3564). Article 9022627 (Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2019.00440

@inproceedings{cdab6520052b46f8bfeaaeb773e3c1a3,

title = "AIM 2019 challenge on image extreme super-resolution: Methods and results",

abstract = "This paper reviews the AIM 2019 challenge on extreme image super-resolution, the problem of restoring of rich details in a low resolution image. Compared to previous, this challenge focuses on an extreme upscaling factor, ×16, and employs the novel DIVerse 8K resolution (DIV8K) dataset. This report focuses on the proposed solutions and final results. The challenge had 2 tracks. The goal in Track 1 was to generate a super-resolution result with high fidelity, using the conventional PSNR as the primary metric to evaluate different methods. Track 2 instead focused on generating visually more pleasant super-resolution results, evaluated using subjective opinions. The two tracks had 71 and 52 registered participants, respectively, and 9 teams competed in the final testing phase. This report gauges the experimental protocol and baselines for the extreme image super-resolution task.",

keywords = "Extreme super resolution",

author = "Shuhang Gu and Hanwen Liu and Dan Zhu and Tangxin Xie and Xin Yang and Chen Zhu and Jia Yu and Wenyu Sun and Xin Tao and Zijun Deng and Liying Lu and Martin Danelljan and Wenbo Li and Taian Guo and Xiaoyong Shen and Xuemiao Xu and Tai, \{Yu Wing\} and Jiaya Jia and Peng Yi and Zhongyuan Wang and Kui Jiang and Junjun Jiang and Radu Timofte and Jiayi Ma and Liu, \{Zhi Song\} and Wang, \{Li Wen\} and Li, \{Chu Tak\} and Siu, \{Wan Chi\} and Chan, \{Yui Lam\} and Ruofan Zhou and Helou, \{Majed Ei\} and Kuldeep Purohit and Praveen Kandula and Muhammad Haris and Maitreya Suin and A. Rajagopalan and Kazutoshi Akita and Greg Shakhnarovic and Norimichi Ukita and \{Navarrete Michelini\}, Pablo and Wenbin Chen",

year = "2019",

month = oct,

day = "27",

doi = "10.1109/ICCVW.2019.00440",

language = "English",

series = "Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019",

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

pages = "3556--3564",

booktitle = "Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019",

note = "17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 ; Conference date: 27-10-2019 Through 28-10-2019",

}

Gu, S, Liu, H, Zhu, D, Xie, T, Yang, X, Zhu, C, Yu, J, Sun, W, Tao, X, Deng, Z, Lu, L, Danelljan, M, Li, W, Guo, T, Shen, X, Xu, X, Tai, YW, Jia, J, Yi, P, Wang, Z, Jiang, K, Jiang, J, Timofte, R, Ma, J, Liu, ZS, Wang, LW, Li, CT, Siu, WC, Chan, YL, Zhou, R, Helou, ME, Purohit, K, Kandula, P, Haris, M, Suin, M, Rajagopalan, A, Akita, K, Shakhnarovic, G, Ukita, N, Navarrete Michelini, P & Chen, W 2019, AIM 2019 challenge on image extreme super-resolution: Methods and results. in Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019., 9022627, Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019, Institute of Electrical and Electronics Engineers Inc., pp. 3556-3564, 17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019, Seoul, Korea, Republic of, 27/10/19. https://doi.org/10.1109/ICCVW.2019.00440

AIM 2019 challenge on image extreme super-resolution: Methods and results. / Gu, Shuhang; Liu, Hanwen; Zhu, Dan et al.
Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 3556-3564 9022627 (Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - AIM 2019 challenge on image extreme super-resolution: Methods and results

AU - Gu, Shuhang

AU - Liu, Hanwen

AU - Zhu, Dan

AU - Xie, Tangxin

AU - Yang, Xin

AU - Zhu, Chen

AU - Yu, Jia

AU - Sun, Wenyu

AU - Tao, Xin

AU - Deng, Zijun

AU - Lu, Liying

AU - Danelljan, Martin

AU - Li, Wenbo

AU - Guo, Taian

AU - Shen, Xiaoyong

AU - Xu, Xuemiao

AU - Tai, Yu Wing

AU - Jia, Jiaya

AU - Yi, Peng

AU - Wang, Zhongyuan

AU - Jiang, Kui

AU - Jiang, Junjun

AU - Timofte, Radu

AU - Ma, Jiayi

AU - Liu, Zhi Song

AU - Wang, Li Wen

AU - Li, Chu Tak

AU - Siu, Wan Chi

AU - Chan, Yui Lam

AU - Zhou, Ruofan

AU - Helou, Majed Ei

AU - Purohit, Kuldeep

AU - Kandula, Praveen

AU - Haris, Muhammad

AU - Suin, Maitreya

AU - Rajagopalan, A.

AU - Akita, Kazutoshi

AU - Shakhnarovic, Greg

AU - Ukita, Norimichi

AU - Navarrete Michelini, Pablo

AU - Chen, Wenbin

PY - 2019/10/27

Y1 - 2019/10/27

N2 - This paper reviews the AIM 2019 challenge on extreme image super-resolution, the problem of restoring of rich details in a low resolution image. Compared to previous, this challenge focuses on an extreme upscaling factor, ×16, and employs the novel DIVerse 8K resolution (DIV8K) dataset. This report focuses on the proposed solutions and final results. The challenge had 2 tracks. The goal in Track 1 was to generate a super-resolution result with high fidelity, using the conventional PSNR as the primary metric to evaluate different methods. Track 2 instead focused on generating visually more pleasant super-resolution results, evaluated using subjective opinions. The two tracks had 71 and 52 registered participants, respectively, and 9 teams competed in the final testing phase. This report gauges the experimental protocol and baselines for the extreme image super-resolution task.

AB - This paper reviews the AIM 2019 challenge on extreme image super-resolution, the problem of restoring of rich details in a low resolution image. Compared to previous, this challenge focuses on an extreme upscaling factor, ×16, and employs the novel DIVerse 8K resolution (DIV8K) dataset. This report focuses on the proposed solutions and final results. The challenge had 2 tracks. The goal in Track 1 was to generate a super-resolution result with high fidelity, using the conventional PSNR as the primary metric to evaluate different methods. Track 2 instead focused on generating visually more pleasant super-resolution results, evaluated using subjective opinions. The two tracks had 71 and 52 registered participants, respectively, and 9 teams competed in the final testing phase. This report gauges the experimental protocol and baselines for the extreme image super-resolution task.

KW - Extreme super resolution

UR - https://www.scopus.com/pages/publications/85082442830

U2 - 10.1109/ICCVW.2019.00440

DO - 10.1109/ICCVW.2019.00440

M3 - Conference article published in proceeding or book

AN - SCOPUS:85082442830

T3 - Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

SP - 3556

EP - 3564

BT - Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019

Y2 - 27 October 2019 through 28 October 2019

ER -

Gu S, Liu H, Zhu D, Xie T, Yang X, Zhu C et al. AIM 2019 challenge on image extreme super-resolution: Methods and results. In Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 3556-3564. 9022627. (Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019). doi: 10.1109/ICCVW.2019.00440

AIM 2019 challenge on image extreme super-resolution: Methods and results

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this