ReF-LLE: Personalized Low-Light Enhancement via Reference-Guided Deep Reinforcement Learning

TL;DR

ReF-LLE introduces a novel personalized low-light image enhancement method using Fourier domain analysis and deep reinforcement learning, effectively adapting to user preferences and varying lighting conditions.

Contribution

It is the first to integrate deep reinforcement learning with Fourier domain techniques for personalized low-light image enhancement.

Findings

Outperforms state-of-the-art methods in perceptual quality.

Effectively adapts to different user preferences.

Handles diverse low-light conditions robustly.

Abstract

Low-light image enhancement presents two primary challenges: 1) Significant variations in low-light images across different conditions, and 2) Enhancement levels influenced by subjective preferences and user intent. To address these issues, we propose ReF-LLE, a novel personalized low-light image enhancement method that operates in the Fourier frequency domain and incorporates deep reinforcement learning. ReF-LLE is the first to integrate deep reinforcement learning into this domain. During training, a zero-reference image evaluation strategy is introduced to score enhanced images, providing reward signals that guide the model to handle varying degrees of low-light conditions effectively. In the inference phase, ReF-LLE employs a personalized adaptive iterative strategy, guided by the zero-frequency component in the Fourier domain, which represents the overall illumination level. This strategy enables the model to adaptively adjust low-light images to align with the illumination distribution of a user-provided reference image, ensuring personalized enhancement results. Extensive experiments on benchmark datasets demonstrate that ReF-LLE outperforms state-of-the-art methods, achieving superior perceptual quality and adaptability in personalized low-light image enhancement.