Saved in:
Bibliographic Details
Main Authors: Zhao, Ming, Liu, Pingping, Zhang, Tongshun, Zhang, Zhe
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.22216
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908425685827584
author Zhao, Ming
Liu, Pingping
Zhang, Tongshun
Zhang, Zhe
author_facet Zhao, Ming
Liu, Pingping
Zhang, Tongshun
Zhang, Zhe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22216
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReF-LLE: Personalized Low-Light Enhancement via Reference-Guided Deep Reinforcement Learning
Zhao, Ming
Liu, Pingping
Zhang, Tongshun
Zhang, Zhe
Computer Vision and Pattern Recognition
Image and Video Processing
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.
title ReF-LLE: Personalized Low-Light Enhancement via Reference-Guided Deep Reinforcement Learning
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2506.22216