ERetinex: Event Camera Meets Retinex Theory for Low-Light Image Enhancement

TL;DR

ERetinex addresses the challenge of low-light RGB image enhancement by fusing asynchronous event-camera data with Retinex theory. It voxelizes event streams into a compact 5-bin representation, jointly estimates illumination via a light-inversion map $L^{-1}$, and performs a two-stage dual-modality fusion to produce a refined image $I_{out}$. Quantitative results on the LIE dataset show PSNR gains of about $1.06$ dB and a substantial $84.28\%$ reduction in FLOPS compared with a recent event-based baseline, while using far fewer parameters. The approach offers robust illumination estimation and detail preservation under extreme lighting, enabling more reliable vision for robotics, surveillance, and other real-world tasks that operate in darkness.

Abstract

Low-light image enhancement aims to restore the under-exposure image captured in dark scenarios. Under such scenarios, traditional frame-based cameras may fail to capture the structure and color information due to the exposure time limitation. Event cameras are bio-inspired vision sensors that respond to pixel-wise brightness changes asynchronously. Event cameras' high dynamic range is pivotal for visual perception in extreme low-light scenarios, surpassing traditional cameras and enabling applications in challenging dark environments. In this paper, inspired by the success of the retinex theory for traditional frame-based low-light image restoration, we introduce the first methods that combine the retinex theory with event cameras and propose a novel retinex-based low-light image restoration framework named ERetinex. Among our contributions, the first is developing a new approach that leverages the high temporal resolution data from event cameras with traditional image information to estimate scene illumination accurately. This method outperforms traditional image-only techniques, especially in low-light environments, by providing more precise lighting information. Additionally, we propose an effective fusion strategy that combines the high dynamic range data from event cameras with the color information of traditional images to enhance image quality. Through this fusion, we can generate clearer and more detail-rich images, maintaining the integrity of visual information even under extreme lighting conditions. The experimental results indicate that our proposed method outperforms state-of-the-art (SOTA) methods, achieving a gain of 1.0613 dB in PSNR while reducing FLOPS by \textbf{84.28}\%.

Figures (5)

• Figure 1: Our ERetinex attains SOTA performance in low-light image reconstruction, demonstrating superior results with fewer parameters.
• Figure 2: The overview of our method. ERetinex illustrates the framework of integrating event-based retinex theory, which consists of an image-event illumination estimator (i) and an Image-Event Dual-Guided Transformer (IEDGT) (ii)
• Figure 3: Illustration of Low-Light Image Restoration Guided by Image and Event Data.
• Figure 4: In this indoor scene, multiple algorithms demonstrate their recovery results. Models with superior performance are enlarged for comparison. It is evident that our model consistently outperforms the others in detail and colour reproduction.
• Figure 5: Three approaches to integrate image and event data: Series I (image-first), Series II (event-first), and Parallel (simultaneous use).