MOFA: A Model Simplification Roadmap for Image Restoration on Mobile Devices

TL;DR

This paper introduces MOFA, a roadmap for simplifying and accelerating image restoration models on mobile devices, improving efficiency and image quality simultaneously.

Contribution

It proposes a novel model simplification roadmap that enhances efficiency and performance of image restoration models specifically for resource-constrained mobile devices.

Findings

Runtime decreased by up to 13%

Parameters reduced by up to 23%

PSNR and SSIM increased on multiple datasets

Abstract

Image restoration aims to restore high-quality images from degraded counterparts and has seen significant advancements through deep learning techniques. The technique has been widely applied to mobile devices for tasks such as mobile photography. Given the resource limitations on mobile devices, such as memory constraints and runtime requirements, the efficiency of models during deployment becomes paramount. Nevertheless, most previous works have primarily concentrated on analyzing the efficiency of single modules and improving them individually. This paper examines the efficiency across different layers. We propose a roadmap that can be applied to further accelerate image restoration models prior to deployment while simultaneously increasing PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index). The roadmap first increases the model capacity by adding more parameters to partial convolutions on FLOPs non-sensitive layers. Then, it applies partial depthwise convolution coupled with decoupling upsampling/downsampling layers to accelerate the model speed. Extensive experiments demonstrate that our approach decreases runtime by up to 13% and reduces the number of parameters by up to 23%, while increasing PSNR and SSIM on several image restoration datasets. Source Code of our method is available at \href{https://github.com/xiangyu8/MOFA}{https://github.com/xiangyu8/MOFA}.