25025

Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report

Andrey Ignatov, Kim Byeoung-su, Radu Timofte, Angeline Pouget, Fenglong Song, Cheng Li, Shuai Xiao, Zhongqian Fu, Matteo Maggioni, Yibin Huang, Shen Cheng, Xin Lu, Yifeng Zhou, Liangyu Chen, Donghao Liu, Xiangyu Zhang, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Minsu Kwon, Myungje Lee, Jaeyoon Yoo, Changbeom Kang, Shinjo Wang, Bin Huang, Tianbao Zhou, Shuai Liu, Lei Lei, Chaoyu Feng, Liguang Huang, Zhikun Lei, Feifei Chen
Mobile AI
arXiv:2105.08629 [eess.IV], (17 May 2021)

@misc{ignatov2021fast,

   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},

   year={2021},

   eprint={2105.08629},

   archivePrefix={arXiv},

   primaryClass={eess.IV}

}

Download Download (PDF)   View View   Source Source   

349

views

Image denoising is one of the most critical problems in mobile photo processing. While many solutions have been proposed for this task, they are usually working with synthetic data and are too computationally expensive to run on mobile devices. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image denoising solution that can demonstrate high efficiency on smartphone GPUs. For this, the participants were provided with a novel large-scale dataset consisting of noisy-clean image pairs captured in the wild. The runtime of all models was evaluated on the Samsung Exynos 2100 chipset with a powerful Mali GPU capable of accelerating floating-point and quantized neural networks. The proposed solutions are fully compatible with any mobile GPU and are capable of processing 480p resolution images under 40-80 ms while achieving high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: