With the popularity of mobile devices, e.g., smartphone and wearable devices, lighter and faster model is crucial for the application of video super resolution. However, most previous lightweight models tend to concentrate on reducing lantency of model inference on desktop GPU, which may be not energy efficient in current mobile devices. In this paper, we proposed Extreme Low-Power Super Resolution (ELSR) network which only consumes a small amount of energy in mobile devices. Pretraining and finetuning methods are applied to boost the performance of the extremely tiny model. Extensive experiments show that our method achieves a excellent balance between restoration quality and power consumption. Finally, we achieve a competitive score of 90.9 with PSNR 27.34 dB and power 0.09 W/30FPS on the target MediaTek Dimensity 9000 plantform, ranking 1st place in the Mobile AI & AIM 2022 Real-Time Video Super-Resolution Challenge.
翻译:由于移动设备(例如智能手机和可磨损设备)的普及性,较轻和更快的模型对于应用视频超分辨率至关重要。然而,大多数以往的轻量型模型往往侧重于减少桌面GPU的模型推断的倾向性,在目前移动设备中,这种模式推断可能没有节能。在本文中,我们提议了只消耗移动设备少量能量的极低级超级分辨率网络(ELSR),采用预先培训和微调方法提高极小模型的性能。广泛的实验表明,我们的方法在恢复质量和电力消耗之间实现了极佳的平衡。最后,我们在目标MediaTek Dimensity 900009 W/30FPS上实现了90.9的竞争性评分,在移动AI和AIM 2022实时视频超级解决方案挑战中排名第一。