AIM 2020 Challenge on Learned Image Signal Processing Pipeline

Abstract

This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original low-quality RAW images captured by the Huawei P20 device to the same photos obtained with the Canon 5D DSLR camera. The considered task embraced a number of complex computer vision subtasks, such as image demosaicing, denoising, white balancing, color and contrast correction, demoireing, 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 the baseline results, defining the state-of-the-art for practical image signal processing pipeline modeling.

Cite

Text

Ignatov et al. "AIM 2020 Challenge on Learned Image Signal Processing Pipeline." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-67070-2_9

Markdown

[Ignatov et al. "AIM 2020 Challenge on Learned Image Signal Processing Pipeline." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/ignatov2020eccvw-aim-a/) doi:10.1007/978-3-030-67070-2_9

BibTeX

@inproceedings{ignatov2020eccvw-aim-a,
  title     = {{AIM 2020 Challenge on Learned Image Signal Processing Pipeline}},
  author    = {Ignatov, Andrey and Timofte, Radu and Zhang, Zhilu and Liu, Ming and Wang, Haolin and Zuo, Wangmeng and Zhang, Jiawei and Zhang, Ruimao and Peng, Zhanglin and Ren, Sijie and Dai, Linhui and Liu, Xiaohong and Li, Chengqi and Chen, Jun and Ito, Yuichi and Vasudeva, Bhavya and Deora, Puneesh and Pal, Umapada and Guo, Zhenyu and Zhu, Yu and Liang, Tian and Li, Chenghua and Leng, Cong and Pan, Zhihong and Li, Baopu and Kim, Byung-Hoon and Song, Joonyoung and Ye, Jong Chul and Baek, JaeHyun and Zhussip, Magauiya and Koishekenov, Yeskendir and Ye, Hwechul Cho and Liu, Xin and Hu, Xueying and Jiang, Jun and Gu, Jinwei and Li, Kai and Tang, Pengliang and Hou, Bingxin},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2020},
  pages     = {152-170},
  doi       = {10.1007/978-3-030-67070-2_9},
  url       = {https://mlanthology.org/eccvw/2020/ignatov2020eccvw-aim-a/}
}