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, "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.
Cite
@article{arxiv.2210.11153,
title = {Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report},
author = {Marcos V. Conde and Radu Timofte and Yibin Huang and Jingyang Peng and Chang Chen and Cheng Li and Eduardo Pérez-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 Juan Marín Vega and Michael Sloth and Peter Schneider-Kamp and Richard Röttger and Furkan Kınlı and Barış Özcan and Furkan Kıraç and Li Leyi and SM Nadim Uddin and Dipon Kumar Ghosh and Yong Ju Jung},
journal= {arXiv preprint arXiv:2210.11153},
year = {2022}
}
Comments
ECCV 2022 Advances in Image Manipulation (AIM) workshop