AIM 2020 Challenge on Learned Image Signal Processing Pipeline

Andrey Ignatov; Radu Timofte; Zhilu Zhang; Ming Liu; Haolin Wang; Wangmeng Zuo; Jiawei Zhang; Ruimao Zhang; Zhanglin Peng; Sijie Ren; Linhui Dai; Xiaohong Liu; Chengqi Li; Jun Chen; Yuichi Ito; Bhavya Vasudeva; Puneesh Deora; Umapada Pal; Zhenyu Guo; Yu Zhu; Tian Liang; Chenghua Li; Cong Leng; Zhihong Pan; Baopu Li; Byung Hoon Kim; Joonyoung Song; Jong Chul Ye; Jae Hyun Baek; Magauiya Zhussip; Yeskendir Koishekenov; Hwechul Cho Ye; Xin Liu; Xueying Hu; Jun Jiang; Jinwei Gu; Kai Li; Pengliang Tan; Bingxin Hou

doi:10.1007/978-3-030-67070-2_9

AIM 2020 Challenge on Learned Image Signal Processing Pipeline

Andrey Ignatov
, Radu Timofte
, Zhilu Zhang
, Ming Liu
, Haolin Wang
, Wangmeng Zuo
, Jiawei Zhang
, Ruimao Zhang
, Zhanglin Peng
, Sijie Ren
, Linhui Dai
, Xiaohong Liu
, Chengqi Li
, Jun Chen
, Yuichi Ito
, Bhavya Vasudeva
, Puneesh Deora
, Umapada Pal
, Zhenyu Guo
, Yu Zhu

Tian Liang, Chenghua Li, Cong Leng, Zhihong Pan, Baopu Li, Byung Hoon Kim, Joonyoung Song, Jong Chul Ye, Jae Hyun Baek, Magauiya Zhussip, Yeskendir Koishekenov, Hwechul Cho Ye, Xin Liu, Xueying Hu, Jun Jiang, Jinwei Gu, Kai Li, Pengliang Tan, Bingxin Hou

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

45 Citations (Scopus)

Abstract

This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original low-quality RAW images captured by the Huawei P20 device to the same photos obtained with the Canon 5D DSLR camera. The considered task embraced a number of complex computer vision subtasks, such as image demosaicing, denoising, white balancing, color and contrast correction, demoireing, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions’ perceptual results measured in a user study. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical image signal processing pipeline modeling.

Original language	English
Title of host publication	Computer Vision – ECCV 2020 Workshops, Proceedings
Editors	Adrien Bartoli, Andrea Fusiello
Pages	152-170
Number of pages	19
DOIs	https://doi.org/10.1007/978-3-030-67070-2_9
Publication status	Published - 2020
Externally published	Yes
Event	Workshops held at the 16th European Conference on Computer Vision, ECCV 2020 - Glasgow, United Kingdom Duration: 23 Aug 2020 → 28 Aug 2020

Publication series

Name	Lecture Notes in Computer Science
Volume	12537 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Workshops held at the 16th European Conference on Computer Vision, ECCV 2020
Country/Territory	United Kingdom
City	Glasgow
Period	23/08/20 → 28/08/20

Access to Document

10.1007/978-3-030-67070-2_9

Cite this

Ignatov, A., Timofte, R., Zhang, Z., Liu, M., Wang, H., Zuo, W., Zhang, J., Zhang, R., Peng, Z., Ren, S., Dai, L., Liu, X., Li, C., Chen, J., Ito, Y., Vasudeva, B., Deora, P., Pal, U., Guo, Z., ... Hou, B. (2020). AIM 2020 Challenge on Learned Image Signal Processing Pipeline. In A. Bartoli, & A. Fusiello (Eds.), Computer Vision – ECCV 2020 Workshops, Proceedings (pp. 152-170). (Lecture Notes in Computer Science; Vol. 12537 LNCS). https://doi.org/10.1007/978-3-030-67070-2_9

@inproceedings{5f93ed334f9245e3b497a1c275231b01,

title = "AIM 2020 Challenge on Learned Image Signal Processing Pipeline",

abstract = "This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original low-quality RAW images captured by the Huawei P20 device to the same photos obtained with the Canon 5D DSLR camera. The considered task embraced a number of complex computer vision subtasks, such as image demosaicing, denoising, white balancing, color and contrast correction, demoireing, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions{\textquoteright} perceptual results measured in a user study. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical image signal processing pipeline modeling.",

author = "Andrey Ignatov and Radu Timofte and Zhilu Zhang and Ming Liu and Haolin Wang and Wangmeng Zuo and Jiawei Zhang and Ruimao Zhang and Zhanglin Peng and Sijie Ren and Linhui Dai and Xiaohong Liu and Chengqi Li and Jun Chen and Yuichi Ito and Bhavya Vasudeva and Puneesh Deora and Umapada Pal and Zhenyu Guo and Yu Zhu and Tian Liang and Chenghua Li and Cong Leng and Zhihong Pan and Baopu Li and Kim, \{Byung Hoon\} and Joonyoung Song and Ye, \{Jong Chul\} and Baek, \{Jae Hyun\} and Magauiya Zhussip and Yeskendir Koishekenov and Ye, \{Hwechul Cho\} and Xin Liu and Xueying Hu and Jun Jiang and Jinwei Gu and Kai Li and Pengliang Tan and Bingxin Hou",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; Workshops held at the 16th European Conference on Computer Vision, ECCV 2020 ; Conference date: 23-08-2020 Through 28-08-2020",

year = "2020",

doi = "10.1007/978-3-030-67070-2\_9",

language = "English",

isbn = "9783030670696",

series = "Lecture Notes in Computer Science",

pages = "152--170",

editor = "Adrien Bartoli and Andrea Fusiello",

booktitle = "Computer Vision – ECCV 2020 Workshops, Proceedings",

}

Ignatov, A, Timofte, R, Zhang, Z, Liu, M, Wang, H, Zuo, W, Zhang, J, Zhang, R, Peng, Z, Ren, S, Dai, L, Liu, X, Li, C, Chen, J, Ito, Y, Vasudeva, B, Deora, P, Pal, U, Guo, Z, Zhu, Y, Liang, T, Li, C, Leng, C, Pan, Z, Li, B, Kim, BH, Song, J, Ye, JC, Baek, JH, Zhussip, M, Koishekenov, Y, Ye, HC, Liu, X, Hu, X, Jiang, J, Gu, J, Li, K, Tan, P & Hou, B 2020, AIM 2020 Challenge on Learned Image Signal Processing Pipeline. in A Bartoli & A Fusiello (eds), Computer Vision – ECCV 2020 Workshops, Proceedings. Lecture Notes in Computer Science, vol. 12537 LNCS, pp. 152-170, Workshops held at the 16th European Conference on Computer Vision, ECCV 2020, Glasgow, United Kingdom, 23/08/20. https://doi.org/10.1007/978-3-030-67070-2_9

AIM 2020 Challenge on Learned Image Signal Processing Pipeline. / Ignatov, Andrey; Timofte, Radu; Zhang, Zhilu et al.
Computer Vision – ECCV 2020 Workshops, Proceedings. ed. / Adrien Bartoli; Andrea Fusiello. 2020. p. 152-170 (Lecture Notes in Computer Science; Vol. 12537 LNCS).

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

TY - GEN

T1 - AIM 2020 Challenge on Learned Image Signal Processing Pipeline

AU - Ignatov, Andrey

AU - Timofte, Radu

AU - Zhang, Zhilu

AU - Liu, Ming

AU - Wang, Haolin

AU - Zuo, Wangmeng

AU - Zhang, Jiawei

AU - Zhang, Ruimao

AU - Peng, Zhanglin

AU - Ren, Sijie

AU - Dai, Linhui

AU - Liu, Xiaohong

AU - Li, Chengqi

AU - Chen, Jun

AU - Ito, Yuichi

AU - Vasudeva, Bhavya

AU - Deora, Puneesh

AU - Pal, Umapada

AU - Guo, Zhenyu

AU - Zhu, Yu

AU - Liang, Tian

AU - Li, Chenghua

AU - Leng, Cong

AU - Pan, Zhihong

AU - Li, Baopu

AU - Kim, Byung Hoon

AU - Song, Joonyoung

AU - Ye, Jong Chul

AU - Baek, Jae Hyun

AU - Zhussip, Magauiya

AU - Koishekenov, Yeskendir

AU - Ye, Hwechul Cho

AU - Liu, Xin

AU - Hu, Xueying

AU - Jiang, Jun

AU - Gu, Jinwei

AU - Li, Kai

AU - Tan, Pengliang

AU - Hou, Bingxin

PY - 2020

Y1 - 2020

N2 - This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original low-quality RAW images captured by the Huawei P20 device to the same photos obtained with the Canon 5D DSLR camera. The considered task embraced a number of complex computer vision subtasks, such as image demosaicing, denoising, white balancing, color and contrast correction, demoireing, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions’ perceptual results measured in a user study. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical image signal processing pipeline modeling.

AB - This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original low-quality RAW images captured by the Huawei P20 device to the same photos obtained with the Canon 5D DSLR camera. The considered task embraced a number of complex computer vision subtasks, such as image demosaicing, denoising, white balancing, color and contrast correction, demoireing, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions’ perceptual results measured in a user study. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical image signal processing pipeline modeling.

UR - https://www.scopus.com/pages/publications/85101541879

U2 - 10.1007/978-3-030-67070-2_9

DO - 10.1007/978-3-030-67070-2_9

M3 - Conference contribution

AN - SCOPUS:85101541879

SN - 9783030670696

T3 - Lecture Notes in Computer Science

SP - 152

EP - 170

BT - Computer Vision – ECCV 2020 Workshops, Proceedings

A2 - Bartoli, Adrien

A2 - Fusiello, Andrea

T2 - Workshops held at the 16th European Conference on Computer Vision, ECCV 2020

Y2 - 23 August 2020 through 28 August 2020

ER -

AIM 2020 Challenge on Learned Image Signal Processing Pipeline

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this