Adaptive Guided Upsampling for Low-light Image Enhancement

TL;DR

This paper presents Adaptive Guided Upsampling (AGU), a novel machine learning approach that enhances low-light images by simultaneously reducing noise and increasing sharpness, outperforming existing methods in real-time applications.

Contribution

The paper introduces AGU, a new multi-parameter optimization method that learns to transfer image characteristics from guidance images to improve low-light image quality.

Findings

AGU achieves superior image enhancement quality compared to state-of-the-art methods.

It operates in real time on low-resolution inputs.

It effectively reduces noise and increases sharpness in low-light images.

Abstract

We introduce Adaptive Guided Upsampling (AGU), an efficient method for upscaling low-light images capable of optimizing multiple image quality characteristics at the same time, such as reducing noise and increasing sharpness. It is based on a guided image method, which transfers image characteristics from a guidance image to the target image. Using state-of-the-art guided methods, low-light images lack sufficient characteristics for this purpose due to their high noise level and low brightness, rendering suboptimal/not significantly improved images in the process. We solve this problem with multi-parameter optimization, learning the association between multiple low-light and bright image characteristics. Our proposed machine learning method learns these characteristics from a few sample images-pairs. AGU can render high-quality images in real time using low-quality, low-resolution input; our experiments demonstrate that it is superior to state-of-the-art methods in the addressed low-light use case.