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

2026-05-21

AI Summary

This work addresses the limitations of existing event-based low-light image enhancement methods, which often neglect global illumination cues and are highly sensitive to real-world event noise. To overcome these issues, the authors propose the EIC-LIE framework, which integrates complementary information through an event-illumination cooperative interaction mechanism and employs an illumination-aware dynamic event filter to effectively suppress noise. Furthermore, they introduce the first high-resolution, temporally synchronized real-world event-image paired dataset, captured using a beamsplitter-based hybrid imaging system. Extensive experiments demonstrate that the proposed method significantly outperforms state-of-the-art approaches across five benchmark datasets, achieving gains of up to 1.24 dB in PSNR and 0.069 in SSIM.

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.

Problem

• low-light image enhancement
• event camera
• illumination
• noise sensitivity
• real-world dataset

Innovation

• event-based imaging
• low-light image enhancement
• illumination-aware filtering
• high-resolution dataset
• event-image fusion