Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latency
This work addresses practical deployment issues for image deblurring on mobile devices, providing guidelines for developers, but it is incremental as it focuses on optimizing existing methods rather than introducing a new paradigm.
The paper tackles the challenge of deploying image deblurring on mobile devices by searching for portable network architectures to optimize the trade-off between quality and latency, demonstrating successful deployment with deep learning accelerators and adoption by a championship-winning team in a 2020 challenge.
Recently, image enhancement and restoration have become important applications on mobile devices, such as super-resolution and image deblurring. However, most state-of-the-art networks present extremely high computational complexity. This makes them difficult to be deployed on mobile devices with acceptable latency. Moreover, when deploying to different mobile devices, there is a large latency variation due to the difference and limitation of deep learning accelerators on mobile devices. In this paper, we conduct a search of portable network architectures for better quality-latency trade-off across mobile devices. We further present the effectiveness of widely used network optimizations for image deblurring task. This paper provides comprehensive experiments and comparisons to uncover the in-depth analysis for both latency and image quality. Through all the above works, we demonstrate the successful deployment of image deblurring application on mobile devices with the acceleration of deep learning accelerators. To the best of our knowledge, this is the first paper that addresses all the deployment issues of image deblurring task across mobile devices. This paper provides practical deployment-guidelines, and is adopted by the championship-winning team in NTIRE 2020 Image Deblurring Challenge on Smartphone Track.