Evaluating Low-Light Image Enhancement Across Multiple Intensity Levels

TL;DR

This paper introduces the MILL dataset for evaluating low-light enhancement methods across various illumination levels and proposes improvements that significantly boost performance and robustness.

Contribution

The paper presents a new multi-illumination dataset and demonstrates how it enables comprehensive evaluation and enhancement of low-light image processing techniques.

Findings

Significant performance variation of methods across different light intensities.

Proposed modifications improve PSNR by up to 10 dB for DSLR images.

The MILL dataset facilitates robust evaluation across diverse lighting conditions.

Abstract

Imaging in low-light environments is challenging due to reduced scene radiance, which leads to elevated sensor noise and reduced color saturation. Most learning-based low-light enhancement methods rely on paired training data captured under a single low-light condition and a well-lit reference. The lack of radiance diversity limits our understanding of how enhancement techniques perform across varying illumination intensities. We introduce the Multi-Illumination Low-Light (MILL) dataset, containing images captured at diverse light intensities under controlled conditions with fixed camera settings and precise illuminance measurements. MILL enables comprehensive evaluation of enhancement algorithms across variable lighting conditions. We benchmark several state-of-the-art methods and reveal significant performance variations across intensity levels. Leveraging the unique multi-illumination structure of our dataset, we propose improvements that enhance robustness across diverse illumination scenarios. Our modifications achieve up to 10 dB PSNR improvement for DSLR and 2 dB for the smartphone on Full HD images.