基于深度学习在移动 GPU 上实现快速相机图像去噪：Mobile AI 2021 挑战赛报告
图像与视频处理
2021-05-19 v1 计算机视觉与模式识别
机器学习
摘要
图像去噪是移动照片处理中最关键的问题之一。尽管已提出许多针对该任务的解决方案，它们通常基于合成数据且计算开销过大，无法在移动设备上运行。为解决此问题，我们引入了首个 Mobile AI 挑战赛，目标是开发一种端到端的基于深度学习的图像去噪方案，能在智能手机 GPU 上展现高效率。为此，我们向参与者提供了一种由实地拍摄的含噪-干净图像对组成的新型大规模数据集。所有模型的运行时间在搭载可加速浮点与量化神经网络的强大 Mali GPU 的三星 Exynos 2100 芯片组上评估。所提方案完全兼容任意移动 GPU，能在 40-80 毫秒内处理 480p 分辨率图像，同时获得高保真结果。本文提供了挑战赛中开发的所有模型的详细描述。
引用
@article{arxiv.2105.08629,
title = {Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report},
author = {Andrey Ignatov and Kim Byeoung-su and Radu Timofte and Angeline Pouget and Fenglong Song and Cheng Li and Shuai Xiao and Zhongqian Fu and Matteo Maggioni and Yibin Huang and Shen Cheng and Xin Lu and Yifeng Zhou and Liangyu Chen and Donghao Liu and Xiangyu Zhang and Haoqiang Fan and Jian Sun and Shuaicheng Liu and Minsu Kwon and Myungje Lee and Jaeyoon Yoo and Changbeom Kang and Shinjo Wang and Bin Huang and Tianbao Zhou and Shuai Liu and Lei Lei and Chaoyu Feng and Liguang Huang and Zhikun Lei and Feifei Chen},
journal= {arXiv preprint arXiv:2105.08629},
year = {2021}
}
备注
Mobile AI 2021 Workshop and Challenges: https://ai-benchmark.com/workshops/mai/2021/. arXiv admin note: substantial text overlap with arXiv:2105.07809, arXiv:2105.07825