A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Aslam, Muhammad Azeem, Khalid, Hassan, Ahmed, Nisar
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908418537684992
author Aslam, Muhammad Azeem
Khalid, Hassan
Ahmed, Nisar
author_facet Aslam, Muhammad Azeem
Khalid, Hassan
Ahmed, Nisar
contents Low-light image enhancement remains a challenging task, particularly in the absence of paired training data. In this study, we present LucentVisionNet, a novel zero-shot learning framework that addresses the limitations of traditional and deep learning-based enhancement methods. The proposed approach integrates multi-scale spatial attention with a deep curve estimation network, enabling fine-grained enhancement while preserving semantic and perceptual fidelity. To further improve generalization, we adopt a recurrent enhancement strategy and optimize the model using a composite loss function comprising six tailored components, including a novel no-reference image quality loss inspired by human visual perception. Extensive experiments on both paired and unpaired benchmark datasets demonstrate that LucentVisionNet consistently outperforms state-of-the-art supervised, unsupervised, and zero-shot methods across multiple full-reference and no-reference image quality metrics. Our framework achieves high visual quality, structural consistency, and computational efficiency, making it well-suited for deployment in real-world applications such as mobile photography, surveillance, and autonomous navigation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18323
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement
Aslam, Muhammad Azeem
Khalid, Hassan
Ahmed, Nisar
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Low-light image enhancement remains a challenging task, particularly in the absence of paired training data. In this study, we present LucentVisionNet, a novel zero-shot learning framework that addresses the limitations of traditional and deep learning-based enhancement methods. The proposed approach integrates multi-scale spatial attention with a deep curve estimation network, enabling fine-grained enhancement while preserving semantic and perceptual fidelity. To further improve generalization, we adopt a recurrent enhancement strategy and optimize the model using a composite loss function comprising six tailored components, including a novel no-reference image quality loss inspired by human visual perception. Extensive experiments on both paired and unpaired benchmark datasets demonstrate that LucentVisionNet consistently outperforms state-of-the-art supervised, unsupervised, and zero-shot methods across multiple full-reference and no-reference image quality metrics. Our framework achieves high visual quality, structural consistency, and computational efficiency, making it well-suited for deployment in real-world applications such as mobile photography, surveillance, and autonomous navigation.
title A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.18323