LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Xu, Lai, Zhihui, Hou, Xianxu, Zhou, Jie, Zhang, Ya-nan, Shen, Linlin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911215224094720
author Wu, Xu
Lai, Zhihui
Hou, Xianxu
Zhou, Jie
Zhang, Ya-nan
Shen, Linlin
author_facet Wu, Xu
Lai, Zhihui
Hou, Xianxu
Zhou, Jie
Zhang, Ya-nan
Shen, Linlin
contents Low-light image enhancement (LLIE) aims to improve illumination while preserving high-quality color and texture. However, existing methods often fail to extract reliable feature representations due to severely degraded pixel-level information under low-light conditions, resulting in poor texture restoration, color inconsistency, and artifact. To address these challenges, we propose LightQANet, a novel framework that introduces quantized and adaptive feature learning for low-light enhancement, aiming to achieve consistent and robust image quality across diverse lighting conditions. From the static modeling perspective, we design a Light Quantization Module (LQM) to explicitly extract and quantify illumination-related factors from image features. By enforcing structured light factor learning, LQM enhances the extraction of light-invariant representations and mitigates feature inconsistency across varying illumination levels. From the dynamic adaptation perspective, we introduce a Light-Aware Prompt Module (LAPM), which encodes illumination priors into learnable prompts to dynamically guide the feature learning process. LAPM enables the model to flexibly adapt to complex and continuously changing lighting conditions, further improving image enhancement. Extensive experiments on multiple low-light datasets demonstrate that our method achieves state-of-the-art performance, delivering superior qualitative and quantitative results across various challenging lighting scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14753
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement
Wu, Xu
Lai, Zhihui
Hou, Xianxu
Zhou, Jie
Zhang, Ya-nan
Shen, Linlin
Computer Vision and Pattern Recognition
Low-light image enhancement (LLIE) aims to improve illumination while preserving high-quality color and texture. However, existing methods often fail to extract reliable feature representations due to severely degraded pixel-level information under low-light conditions, resulting in poor texture restoration, color inconsistency, and artifact. To address these challenges, we propose LightQANet, a novel framework that introduces quantized and adaptive feature learning for low-light enhancement, aiming to achieve consistent and robust image quality across diverse lighting conditions. From the static modeling perspective, we design a Light Quantization Module (LQM) to explicitly extract and quantify illumination-related factors from image features. By enforcing structured light factor learning, LQM enhances the extraction of light-invariant representations and mitigates feature inconsistency across varying illumination levels. From the dynamic adaptation perspective, we introduce a Light-Aware Prompt Module (LAPM), which encodes illumination priors into learnable prompts to dynamically guide the feature learning process. LAPM enables the model to flexibly adapt to complex and continuously changing lighting conditions, further improving image enhancement. Extensive experiments on multiple low-light datasets demonstrate that our method achieves state-of-the-art performance, delivering superior qualitative and quantitative results across various challenging lighting scenarios.
title LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.14753