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

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 sce...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Conde, Marcos V, Timofte, Radu, Huang, Yibin, Jingyang Peng, Chen, Chang, Cheng, Li, Pérez-Pellitero, Eduardo, Song, Fenglong, Bai, Furui, Liu, Shuai, Feng, Chaoyu, Wang, Xiaotao, Lei, Lei, Zhu, Yu, Li, Chenghua, Jiang, Yingying, Yong, A, Wang, Peisong, Leng, Cong, Cheng, Jian, Liu, Xiaoyu, Yin, Zhicun, Zhang, Zhilu, Li, Junyi, Liu, Ming, Zuo, Wangmeng, Jiang, Jun, Kim, Jinha, Zhang, Yue, Zou, Beiji, Zong, Zhikai, Liu, Xiaoxiao, Juan Marín Vega, Sloth, Michael, Schneider-Kamp, Peter, Röttger, Richard, Kınlı, Furkan, Özcan, Barış, Kıraç, Furkan, Li Leyi, SM Nadim Uddin, Ghosh, Dipon Kumar, Jung, Yong Ju
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 20.10.2022
Subjects
Color imagery
Datasets
Image reconstruction
Inverse problems
Irradiance
Microprocessors
Noise reduction
Signal processing
Vision
White balancing
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422