MIPI 2022 Challenge on Quad-Bayer Re-Mosaic: Dataset and Report
Abstract
Developing and integrating advanced image sensors with novel algorithms in camera systems is prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lack of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). To bridge the gap, we introduce the first MIPI challenge including five tracks focusing on novel image sensors and imaging algorithms. In this paper, Quad Joint Remosaic and Denoise, one of the five tracks, working on the interpolation of Quad CFA to Bayer at full-resolution is introduced. The participants were provided with a new dataset including 70 (training) and 15 (validation) scenes of high-quality Quad and Bayer pair. In addition, for each scene, Quad of different noise level were provided at 0 dB, 24 dB and 42 dB. All the data were captured using a Quad sensor in both outdoor and indoor conditions. The final results are evaluated using objective metrics including PSNR, SSIM [ 6 ], LPIPS [ 10 ] and KLD. A detailed description of all models developed in this challenge is provided in this paper. More details of this challenge and the link to the dataset can be found in https://github.com/mipi-challenge/MIPI2022 .
Cite
Text
Yang et al. "MIPI 2022 Challenge on Quad-Bayer Re-Mosaic: Dataset and Report." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25072-9_2Markdown
[Yang et al. "MIPI 2022 Challenge on Quad-Bayer Re-Mosaic: Dataset and Report." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/yang2022eccvw-mipi-b/) doi:10.1007/978-3-031-25072-9_2BibTeX
@inproceedings{yang2022eccvw-mipi-b,
title = {{MIPI 2022 Challenge on Quad-Bayer Re-Mosaic: Dataset and Report}},
author = {Yang, Qingyu and Yang, Guang and Jiang, Jun and Li, Chongyi and Feng, Ruicheng and Zhou, Shangchen and Sun, Wenxiu and Zhu, Qingpeng and Loy, Chen Change and Gu, Jinwei and Wang, Zhen and Li, Daoyu and Zhang, Yuzhe and Peng, Lintao and Chang, Xuyang and Zhang, Yinuo and Wu, Yaqi and Wu, Xun and Fan, Zhihao and Xia, Chengjie and Zhang, Feng and Zeng, Haijin and Feng, Kai and Zhao, Yongqiang and Luong, Hiêp Quang and Aelterman, Jan and Truong, Anh Minh and Philips, Wilfried and Liu, Xiaohong and Jia, Jun and Sun, Hanchi and Zhai, Guangtao and Xiao, Longan and Xu, Qihang and Jiang, Ting and Wu, Qi and Jiang, Chengzhi and Han, Mingyan and Li, Xinpeng and Lin, Wenjie and Li, Youwei and Fan, Haoqiang and Liu, Shuaicheng and Wu, Rongyuan and Sun, Lingchen and Yi, Qiaosi},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {21-35},
doi = {10.1007/978-3-031-25072-9_2},
url = {https://mlanthology.org/eccvw/2022/yang2022eccvw-mipi-b/}
}