Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset

TL;DR

This paper introduces a novel event-illumination collaborative framework for low-light image enhancement, utilizing a high-resolution real-world dataset and new modules to improve noise reduction and illumination handling.

Contribution

The paper proposes the EIC-LIE framework with innovative modules and a new dataset, advancing real-world event-based low-light image enhancement techniques.

Findings

Outperforms state-of-the-art methods on five datasets

Achieves up to 1.24dB PSNR improvement

Significantly reduces event noise based on brightness statistics

Abstract

Event-based low-light image enhancement (LIE) methods mainly focus on incorporating high dynamic range (HDR) information from events while overlooking the essential global illumination in images and the inherent noise sensitivity of event signals in real-world scenarios. To address these issues, we propose EIC-LIE, an event-illumination collaborative LIE framework. Concretely, we first design an Event-Illumination Collaborative Interaction (EICI) module, which contains two key processes: forward gathering, which gathers HDR features across varying lighting conditions, and backward injection, which provides complementary content for illumination and event representations. Next, we introduce an Illumination-aware Event Filter (IAEF) that dynamically reduces event noise based on brightness statistics derived from images. Additionally, we build a beam-splitter-based hybrid imaging system to collect high-quality event-image pairs with temporal synchronization from dynamic scenes, providing the first high-resolution, real-world event-based LIE dataset. Extensive experiments show that our EIC-LIE outperforms state-of-the-art methods on five real-world and synthetic datasets, significantly surpassing previous methods with improvements of up to 1.24dB in PSNR and 0.069 in SSIM. The code and dataset are released at https://github.com/QUEAHREN/EIC-LIE.