Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report
Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report
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.
Dan Zhu、Wenxu Wang、Qinghua Zheng、Hengxing Cai、Biao Wu、Weizhan Zhang、Steve Kim、Xiao Sun、Caixia Yan、Xuncheng Liu、Wei Chen、Ning Wang、Qi Wang、Yu-Syuan Xu、Chia-Ming Cheng、Hojin Cho、Zehua Cheng、Hong-Han Shuai、Andrey Ignatov、Wenyi Lian、Wen-Huang Cheng、Ran Duan、Guannan Chen、Li Liu、Shaoli Liu、Shijie Yue、Haipeng Du、Wangdu Chen、Long Bao、Chih-Cheng Chen、Xiaochen Cai、Chengjian Zheng、Si Gao、Zhengyang Zhuge、Kaidi Lu、Yijian Zhang、Hsien-Kai Kuo、Wenjing Lian、Xiaofeng Zhang、Allen Lu、Kele Xu、Zhuang Jia、Diankai Zhang、Mengdi Sun、HaoDong Wu、Chenghua Li、Yufeng Zhou、Cheng-Ming Chiang、Heng Sun、Jia-Ying Yong、Ran Duan、Tianyu Xu、Radu Timofte、Man-Yu Lee
微电子学、集成电路计算技术、计算机技术电子技术应用
Dan Zhu,Wenxu Wang,Qinghua Zheng,Hengxing Cai,Biao Wu,Weizhan Zhang,Steve Kim,Xiao Sun,Caixia Yan,Xuncheng Liu,Wei Chen,Ning Wang,Qi Wang,Yu-Syuan Xu,Chia-Ming Cheng,Hojin Cho,Zehua Cheng,Hong-Han Shuai,Andrey Ignatov,Wenyi Lian,Wen-Huang Cheng,Ran Duan,Guannan Chen,Li Liu,Shaoli Liu,Shijie Yue,Haipeng Du,Wangdu Chen,Long Bao,Chih-Cheng Chen,Xiaochen Cai,Chengjian Zheng,Si Gao,Zhengyang Zhuge,Kaidi Lu,Yijian Zhang,Hsien-Kai Kuo,Wenjing Lian,Xiaofeng Zhang,Allen Lu,Kele Xu,Zhuang Jia,Diankai Zhang,Mengdi Sun,HaoDong Wu,Chenghua Li,Yufeng Zhou,Cheng-Ming Chiang,Heng Sun,Jia-Ying Yong,Ran Duan,Tianyu Xu,Radu Timofte,Man-Yu Lee.Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report[EB/OL].(2022-11-07)[2025-08-21].https://arxiv.org/abs/2211.05256.点此复制
评论