AIM 2019 Challenge on RAW to RGB Mapping: Methods and Results

Abstract

This paper reviews the first AIM challenge on mapping camera RAW to RGB images with the focus on proposed solutions and results. The participating teams were solving a real-world photo enhancement problem, where the goal was to map the original low-quality RAW images from the Huawei P20 device to the same photos captured with the Canon 5D DSLR camera. The considered problem embraced a number of computer vision subtasks, such as image demosaicing, denoising, gamma correction, image resolution and sharpness enhancement, 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 baseline results, defining the state-of-the-art for RAW to RGB image restoration.

Cite

Text

Ignatov et al. "AIM 2019 Challenge on RAW to RGB Mapping: Methods and Results." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00443

Markdown

[Ignatov et al. "AIM 2019 Challenge on RAW to RGB Mapping: Methods and Results." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/ignatov2019iccvw-aim-a/) doi:10.1109/ICCVW.2019.00443

BibTeX

@inproceedings{ignatov2019iccvw-aim-a,
  title     = {{AIM 2019 Challenge on RAW to RGB Mapping: Methods and Results}},
  author    = {Ignatov, Andrey and Li, Juncheng and Zhang, Jiajie and Wu, Haoyu and Li, Jie and Huang, Rui and Haris, Muhammad and Shakhnarovich, Greg and Ukita, Norimichi and Zhao, Yuzhi and Po, Lai-Man and Timofte, Radu and Zhang, Tiantian and Liao, Zongbang and Shi, Xiang and Zhang, Yujia and Ou, Weifeng and Xian, Pengfei and Xiong, Jingjing and Zhou, Chang and Yu, Wing Yin and Yubin, Yubin and Ko, Sung-Jea and Hou, Bingxin and Park, Bumjun and Yu, Songhyun and Kim, Sangmin and Jeong, Jechang and Kim, Seung-Wook and Uhm, Kwang-Hyun and Ji, Seo-Won and Cho, Sung-Jin and Hong, Jun-Pyo and Mei, Kangfu},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {3584-3590},
  doi       = {10.1109/ICCVW.2019.00443},
  url       = {https://mlanthology.org/iccvw/2019/ignatov2019iccvw-aim-a/}
}