ML Anthology

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 Kinli, Baris Özcan, Furkan Kiraç, Li Leyi, S. M. Nadim Uddin, Dipon Kumar Ghosh, Yong Ju Jung
ECCVW 2022 pp. 3-26
doi:10.1007/978-3-031-25066-8_1 /eccvw/2022/conde2022eccvw-reversed/

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.

PDF ECCVW Semantic Scholar

Cite

Text

Conde et al. "Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25066-8_1

Markdown

[Conde et al. "Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/conde2022eccvw-reversed/) doi:10.1007/978-3-031-25066-8_1

BibTeX

@inproceedings{conde2022eccvw-reversed,
  title     = {{Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report}},
  author    = {Conde, Marcos V. and Timofte, Radu and Huang, Yibin and Peng, Jingyang and Chen, Chang and Li, Cheng and Pérez-Pellitero, Eduardo and Song, Fenglong and Bai, Furui and Liu, Shuai and Feng, Chaoyu and Wang, Xiaotao and Lei, Lei and Zhu, Yu and Li, Chenghua and Jiang, Yingying and A, Yong and Wang, Peisong and Leng, Cong and Cheng, Jian and Liu, Xiaoyu and Yin, Zhicun and Zhang, Zhilu and Li, Junyi and Liu, Ming and Zuo, Wangmeng and Jiang, Jun and Kim, Jinha and Zhang, Yue and Zou, Beiji and Zong, Zhikai and Liu, Xiaoxiao and Marín-Vega, Juan and Sloth, Michael and Schneider-Kamp, Peter and Röttger, Richard and Kinli, Furkan and Özcan, Baris and Kiraç, Furkan and Leyi, Li and Uddin, S. M. Nadim and Ghosh, Dipon Kumar and Jung, Yong Ju},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2022},
  pages     = {3-26},
  doi       = {10.1007/978-3-031-25066-8_1},
  url       = {https://mlanthology.org/eccvw/2022/conde2022eccvw-reversed/}
}