# Fast Perceptual Image Enhancement

## TL;DR

This paper presents a lightweight neural network architecture for mobile image enhancement that improves image quality and processing speed, making high-quality photo enhancement feasible on mobile devices.

## Contribution

It introduces an efficient network design that enhances image quality and speeds up processing by over six times compared to previous models, suitable for mobile hardware.

## Key findings

- Achieves higher mean opinion scores than baseline models.
- Speeds up computation by 6.3 times on a consumer CPU.
- Supports real-time mobile image enhancement.

## Abstract

The vast majority of photos taken today are by mobile phones. While their quality is rapidly growing, due to physical limitations and cost constraints, mobile phone cameras struggle to compare in quality with DSLR cameras. This motivates us to computationally enhance these images. We extend upon the results of Ignatov et al., where they are able to translate images from compact mobile cameras into images with comparable quality to high-resolution photos taken by DSLR cameras. However, the neural models employed require large amounts of computational resources and are not lightweight enough to run on mobile devices. We build upon the prior work and explore different network architectures targeting an increase in image quality and speed. With an efficient network architecture which does most of its processing in a lower spatial resolution, we achieve a significantly higher mean opinion score (MOS) than the baseline while speeding up the computation by 6.3 times on a consumer-grade CPU. This suggests a promising direction for neural-network-based photo enhancement using the phone hardware of the future.