تقرير
Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report
| العنوان: | Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report |
|---|---|
| المؤلفون: | Ignatov, Andrey, Timofte, Radu, Chiang, Cheng-Ming, Kuo, Hsien-Kai, Xu, Yu-Syuan, Lee, Man-Yu, Lu, Allen, Cheng, Chia-Ming, Chen, Chih-Cheng, Yong, Jia-Ying, Shuai, Hong-Han, Cheng, Wen-Huang, Jia, Zhuang, Xu, Tianyu, Zhang, Yijian, Bao, Long, Sun, Heng, Zhang, Diankai, Gao, Si, Liu, Shaoli, Wu, Biao, Zhang, Xiaofeng, Zheng, Chengjian, Lu, Kaidi, Wang, Ning, Sun, Xiao, Wu, HaoDong, Liu, Xuncheng, Zhang, Weizhan, Yan, Caixia, Du, Haipeng, Zheng, Qinghua, Wang, Qi, Chen, Wangdu, Duan, Ran, Sun, Mengdi, Zhu, Dan, Chen, Guannan, Cho, Hojin, Kim, Steve, Yue, Shijie, Li, Chenghua, Zhuge, Zhengyang, Chen, Wei, Wang, Wenxu, Zhou, Yufeng, Cai, Xiaochen, Cai, Hengxing, Xu, Kele, Liu, Li, Cheng, Zehua, Lian, Wenyi, Lian, Wenjing |
| سنة النشر: | 2022 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper. Comment: arXiv admin note: text overlap with arXiv:2105.08826, arXiv:2105.07809, arXiv:2211.04470, arXiv:2211.03885 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2211.05256 |
| رقم الأكسشن: | edsarx.2211.05256 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |