Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report

Marcos V. Conde; Radu Timofte; Yibin Huang; Jingyang Peng; Chang Chen; Cheng Li; Eduardo Pérez-Pellitero; Fenglong Song; Furui Bai; Shuai Liu; Chaoyu Feng; Xiaotao Wang; Lei Lei; Yu Zhu; Chenghua Li; Yingying Jiang; Yong A; Peisong Wang; Cong Leng; Jian Cheng; Xiaoyu Liu; Zhicun Yin; Zhilu Zhang; Junyi Li; Ming Liu; Wangmeng Zuo; Jun Jiang; Jinha Kim; Yue Zhang; Beiji Zou; Zhikai Zong; Xiaoxiao Liu; Juan Marín Vega; Michael Sloth; Peter Schneider-Kamp; Richard Röttger; Furkan Kınlı; Barış Özcan; Furkan Kıraç; Li Leyi; S. M.Nadim Uddin; Dipon Kumar Ghosh; Yong Ju Jung

doi:10.1007/978-3-031-25066-8_1

Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report

Marcos V. Conde^*
, Radu Timofte
, Yibin Huang
, Jingyang Peng
, Chang Chen
, Cheng Li
, Eduardo Pérez-Pellitero
, Fenglong Song
, Furui Bai
, Shuai Liu
, Chaoyu Feng
, Xiaotao Wang
, Lei Lei
, Yu Zhu
, Chenghua Li
, Yingying Jiang
, Yong A
, Peisong Wang
, Cong Leng
, Jian Cheng

Xiaoyu Liu, Zhicun Yin, Zhilu Zhang, Junyi Li, Ming Liu, Wangmeng Zuo, Jun Jiang, Jinha Kim, Yue Zhang, Beiji Zou, Zhikai Zong, Xiaoxiao Liu, Juan Marín Vega, Michael Sloth, Peter Schneider-Kamp, Richard Röttger, Furkan Kınlı, Barış Özcan, Furkan Kıraç, Li Leyi, S. M.Nadim Uddin, Dipon Kumar Ghosh, Yong Ju Jung

^*Corresponding author for this work

University of Würzburg

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

13 Scopus citations

Abstract

Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white balance) due to its linear relationship with the scene irradiance, wide-range of information at 12bits, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public RGB datasets. This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, “reverse” the ISP transformation. The proposed methods and benchmark establish the state-of-the-art for this low-level vision inverse problem, and generating realistic raw sensor readings can potentially benefit other tasks such as denoising and super-resolution.

Original language	English
Title of host publication	Computer Vision – ECCV 2022 Workshops, Proceedings
Editors	Leonid Karlinsky, Tomer Michaeli, Ko Nishino
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	3-26
Number of pages	24
ISBN (Print)	9783031250651
DOIs	https://doi.org/10.1007/978-3-031-25066-8_1
State	Published - 2023
Externally published	Yes
Event	Workshops held at the 17th European Conference on Computer Vision, ECCV 2022 - Tel Aviv, Israel Duration: 23 Oct 2022 → 27 Oct 2022

Publication series

Name	Lecture Notes in Computer Science
Volume	13803 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Workshops held at the 17th European Conference on Computer Vision, ECCV 2022
Country/Territory	Israel
City	Tel Aviv
Period	23/10/22 → 27/10/22

Keywords

Computational photography
Image signal processing
Image synthesis
Inverse problems
Low-level vision
Raw images

Access to Document

10.1007/978-3-031-25066-8_1

Cite this

Conde, M. V., Timofte, R., Huang, Y., Peng, J., Chen, C., Li, C., Pérez-Pellitero, E., Song, F., Bai, F., Liu, S., Feng, C., Wang, X., Lei, L., Zhu, Y., Li, C., Jiang, Y., A, Y., Wang, P., Leng, C., ... Ju Jung, Y. (2023). Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report. In L. Karlinsky, T. Michaeli, & K. Nishino (Eds.), Computer Vision – ECCV 2022 Workshops, Proceedings (pp. 3-26). (Lecture Notes in Computer Science; Vol. 13803 LNCS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-25066-8_1

@inproceedings{24aa173b441f48419c9d1002fcda9580,

title = "Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report",

abstract = "Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white balance) due to its linear relationship with the scene irradiance, wide-range of information at 12bits, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public RGB datasets. This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, {\textquotedblleft}reverse{\textquotedblright} the ISP transformation. The proposed methods and benchmark establish the state-of-the-art for this low-level vision inverse problem, and generating realistic raw sensor readings can potentially benefit other tasks such as denoising and super-resolution.",

keywords = "Computational photography, Image signal processing, Image synthesis, Inverse problems, Low-level vision, Raw images",

author = "Conde, \{Marcos V.\} and Radu Timofte and Yibin Huang and Jingyang Peng and Chang Chen and Cheng Li and Eduardo P{\'e}rez-Pellitero and Fenglong Song and Furui Bai and Shuai Liu and Chaoyu Feng and Xiaotao Wang and Lei Lei and Yu Zhu and Chenghua Li and Yingying Jiang and Yong A and Peisong Wang and Cong Leng and Jian Cheng and Xiaoyu Liu and Zhicun Yin and Zhilu Zhang and Junyi Li and Ming Liu and Wangmeng Zuo and Jun Jiang and Jinha Kim and Yue Zhang and Beiji Zou and Zhikai Zong and Xiaoxiao Liu and \{Mar{\'i}n Vega\}, Juan and Michael Sloth and Peter Schneider-Kamp and Richard R{\"o}ttger and Furkan Kınlı and Barı{\c s} {\"O}zcan and Furkan Kıra{\c c} and Li Leyi and Uddin, \{S. M.Nadim\} and Ghosh, \{Dipon Kumar\} and \{Ju Jung\}, Yong",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Workshops held at the 17th European Conference on Computer Vision, ECCV 2022 ; Conference date: 23-10-2022 Through 27-10-2022",

year = "2023",

doi = "10.1007/978-3-031-25066-8\_1",

language = "英语",

isbn = "9783031250651",

series = "Lecture Notes in Computer Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "3--26",

editor = "Leonid Karlinsky and Tomer Michaeli and Ko Nishino",

booktitle = "Computer Vision {\textendash} ECCV 2022 Workshops, Proceedings",

address = "德国",

}

Conde, MV, Timofte, R, Huang, Y, Peng, J, Chen, C, Li, C, Pérez-Pellitero, E, Song, F, Bai, F, Liu, S, Feng, C, Wang, X, Lei, L, Zhu, Y, Li, C, Jiang, Y, A, Y, Wang, P, Leng, C, Cheng, J, Liu, X, Yin, Z, Zhang, Z, Li, J , Liu, M , Zuo, W, Jiang, J, Kim, J, Zhang, Y, Zou, B, Zong, Z, Liu, X, Marín Vega, J, Sloth, M, Schneider-Kamp, P, Röttger, R, Kınlı, F, Özcan, B, Kıraç, F, Leyi, L, Uddin, SMN, Ghosh, DK & Ju Jung, Y 2023, Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report. in L Karlinsky, T Michaeli & K Nishino (eds), Computer Vision – ECCV 2022 Workshops, Proceedings. Lecture Notes in Computer Science, vol. 13803 LNCS, Springer Science and Business Media Deutschland GmbH, pp. 3-26, Workshops held at the 17th European Conference on Computer Vision, ECCV 2022, Tel Aviv, Israel, 23/10/22. https://doi.org/10.1007/978-3-031-25066-8_1

Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report. / Conde, Marcos V.; Timofte, Radu; Huang, Yibin et al.
Computer Vision – ECCV 2022 Workshops, Proceedings. ed. / Leonid Karlinsky; Tomer Michaeli; Ko Nishino. Springer Science and Business Media Deutschland GmbH, 2023. p. 3-26 (Lecture Notes in Computer Science; Vol. 13803 LNCS).

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

TY - GEN

T1 - Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report

AU - Conde, Marcos V.

AU - Timofte, Radu

AU - Huang, Yibin

AU - Peng, Jingyang

AU - Chen, Chang

AU - Li, Cheng

AU - Pérez-Pellitero, Eduardo

AU - Song, Fenglong

AU - Bai, Furui

AU - Liu, Shuai

AU - Feng, Chaoyu

AU - Wang, Xiaotao

AU - Lei, Lei

AU - Zhu, Yu

AU - Li, Chenghua

AU - Jiang, Yingying

AU - A, Yong

AU - Wang, Peisong

AU - Leng, Cong

AU - Cheng, Jian

AU - Liu, Xiaoyu

AU - Yin, Zhicun

AU - Zhang, Zhilu

AU - Li, Junyi

AU - Liu, Ming

AU - Zuo, Wangmeng

AU - Jiang, Jun

AU - Kim, Jinha

AU - Zhang, Yue

AU - Zou, Beiji

AU - Zong, Zhikai

AU - Liu, Xiaoxiao

AU - Marín Vega, Juan

AU - Sloth, Michael

AU - Schneider-Kamp, Peter

AU - Röttger, Richard

AU - Kınlı, Furkan

AU - Özcan, Barış

AU - Kıraç, Furkan

AU - Leyi, Li

AU - Uddin, S. M.Nadim

AU - Ghosh, Dipon Kumar

AU - Ju Jung, Yong

PY - 2023

Y1 - 2023

N2 - Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white balance) due to its linear relationship with the scene irradiance, wide-range of information at 12bits, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public RGB datasets. This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, “reverse” the ISP transformation. The proposed methods and benchmark establish the state-of-the-art for this low-level vision inverse problem, and generating realistic raw sensor readings can potentially benefit other tasks such as denoising and super-resolution.

AB - Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white balance) due to its linear relationship with the scene irradiance, wide-range of information at 12bits, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public RGB datasets. This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, “reverse” the ISP transformation. The proposed methods and benchmark establish the state-of-the-art for this low-level vision inverse problem, and generating realistic raw sensor readings can potentially benefit other tasks such as denoising and super-resolution.

KW - Computational photography

KW - Image signal processing

KW - Image synthesis

KW - Inverse problems

KW - Low-level vision

KW - Raw images

UR - https://www.scopus.com/pages/publications/85151147357

U2 - 10.1007/978-3-031-25066-8_1

DO - 10.1007/978-3-031-25066-8_1

M3 - 会议稿件

AN - SCOPUS:85151147357

SN - 9783031250651

T3 - Lecture Notes in Computer Science

SP - 3

EP - 26

BT - Computer Vision – ECCV 2022 Workshops, Proceedings

A2 - Karlinsky, Leonid

A2 - Michaeli, Tomer

A2 - Nishino, Ko

PB - Springer Science and Business Media Deutschland GmbH

T2 - Workshops held at the 17th European Conference on Computer Vision, ECCV 2022

Y2 - 23 October 2022 through 27 October 2022

ER -

Conde MV, Timofte R, Huang Y, Peng J, Chen C, Li C et al. Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report. In Karlinsky L, Michaeli T, Nishino K, editors, Computer Vision – ECCV 2022 Workshops, Proceedings. Springer Science and Business Media Deutschland GmbH. 2023. p. 3-26. (Lecture Notes in Computer Science). doi: 10.1007/978-3-031-25066-8_1