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

2025-03-04

AI Summary

This work addresses the degradation of structural and chromatic information in frame-based cameras under extremely low-light conditions due to exposure constraints. To this end, we propose a novel low-light image enhancement method—the first to integrate event cameras with Retinex theory. Methodologically, we establish an event-image collaborative Retinex decomposition framework, introduce a new paradigm for illumination estimation based on spatiotemporal encoding of event streams, and incorporate multimodal feature alignment with a lightweight cross-modal fusion network to jointly achieve detail recovery and color fidelity. Extensive experiments demonstrate that our approach achieves a 1.06 dB PSNR improvement over state-of-the-art methods while reducing computational complexity by 84.3% (FLOPs). It significantly enhances structural clarity, texture reconstruction accuracy, and color fidelity in ultra-dim scenes.

Technology Category

• Computer Vision: Image and Video Retrieval
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Data transparency and provenance

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 extbf{84.28}%.

Problem

• Enhance low-light images using event cameras and Retinex theory.
• Combine high dynamic range data with traditional image color information.
• Improve image quality in extreme low-light conditions effectively.

Innovation

• Combines Retinex theory with event cameras
• Fuses high dynamic range and color data
• Enhances low-light images with high precision