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

2025-06-27

AI Summary

Low-light image enhancement faces two major challenges: significant environmental variability and subjective user preferences. To address these, this paper proposes a reference-guided deep reinforcement learning (DRL) framework for personalized enhancement in the Fourier frequency domain. It is the first to introduce DRL into frequency-domain modeling for low-light enhancement. We design a no-reference image quality assessment strategy that leverages the luminance distribution of a reference image to guide adaptive frequency-domain adjustments. Furthermore, we establish a personalized iterative optimization mechanism that dynamically refines enhancement parameters based on perceptual feedback. Extensive experiments on multiple benchmark datasets demonstrate that our method consistently outperforms existing state-of-the-art approaches, achieving superior perceptual naturalness and improved alignment with user intent. The framework successfully balances objective fidelity—preserving structural integrity and color accuracy—with subjective acceptability—ensuring visually pleasing and contextually appropriate results.

Technology Category

• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV
• Machine Learning: Reinforcement Learning

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Privacy-enhancing technologies

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.

Problem

• Handles diverse low-light image conditions adaptively
• Incorporates user preferences for personalized enhancement
• Uses Fourier domain and reinforcement learning for optimization

Innovation

• Fourier domain deep reinforcement learning
• Zero-reference image evaluation strategy
• Personalized adaptive iterative enhancement