Low-Light Image Enhancement using Event-Based Illumination Estimation

2025-04-13

AI Summary

Low-light image enhancement (LLIE) suffers from overreliance on motion-dominated events and fails to exploit the high dynamic range and low-light sensitivity advantages of event cameras. This paper introduces, for the first time, a transmission-modulated “temporal-mapped event” framework to estimate pixel-wise illumination by mapping event timestamps to luminance values, enabling illumination-guided, fine-grained decomposition and enhancement of the reflectance component. Our contributions are threefold: (1) a novel illumination-guided reflectance enhancement paradigm; (2) EvLowLight—the first real-world, synchronized dataset jointly featuring temporal-mapped and motion events; and (3) a degradation model characterizing temporal-mapped event distortion under low-light conditions. The proposed method integrates event modeling, timestamp-to-luminance mapping, and a reflectance decomposition network. It achieves state-of-the-art performance on five synthetic benchmarks and EvLowLight, improving PSNR by 6.62 dB and attaining 35.6 FPS inference speed at 640×480 resolution.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Low-light image enhancement (LLIE) aims to improve the visibility of images captured in poorly lit environments. Prevalent event-based solutions primarily utilize events triggered by motion, i.e., ''motion events'' to strengthen only the edge texture, while leaving the high dynamic range and excellent low-light responsiveness of event cameras largely unexplored. This paper instead opens a new avenue from the perspective of estimating the illumination using ''temporal-mapping'' events, i.e., by converting the timestamps of events triggered by a transmittance modulation into brightness values. The resulting fine-grained illumination cues facilitate a more effective decomposition and enhancement of the reflectance component in low-light images through the proposed Illumination-aided Reflectance Enhancement module. Furthermore, the degradation model of temporal-mapping events under low-light condition is investigated for realistic training data synthesizing. To address the lack of datasets under this regime, we construct a beam-splitter setup and collect EvLowLight dataset that includes images, temporal-mapping events, and motion events. Extensive experiments across 5 synthetic datasets and our real-world EvLowLight dataset substantiate that the devised pipeline, dubbed RetinEV, excels in producing well-illuminated, high dynamic range images, outperforming previous state-of-the-art event-based methods by up to 6.62 dB, while maintaining an efficient inference speed of 35.6 frame-per-second on a 640X480 image.

Problem

• Enhancing low-light images using event-based illumination estimation
• Utilizing temporal-mapping events for better reflectance decomposition
• Addressing lack of datasets with EvLowLight collection

Innovation

• Uses temporal-mapping events for illumination estimation
• Proposes Illumination-aided Reflectance Enhancement module
• Introduces EvLowLight dataset for realistic training