Low-Light Image Enhancement Guided by Hybrid Explicit-Implicit Semantics
Sensors · 06.11.2026 · 26 (21) · 7019
DOI: 10.3390/s26217019 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 06.11.2026. Verfasst von Zanhao Liang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan 430074, China. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Low-light image enhancement (LLIE) is fundamentally a restoration problem rather than a brightness adjustment task, as it aims to recover the underlying scene information from images captured under low signal-to-noise ratio conditions. However, most existing methods adopt globally uniform enhancement schemes and overlook the degradation discrepancies across semantic regions, limiting overall performance. Recent semantic-guided LLIE methods often neglect how low-light degradation impairs the fidelity of semantic priors, preventing them from exploiting semantic information. To address these issues, we propose an implicit semantic guidance branch that employs a Light-up Module and a Feature Alignment Module to obtain accurate semantic features and adaptively integrate them into the feature representation space. Furthermore, we introduce an explicit semantic guidance branch that constructs a Semantic-Guided Pixel Consistency Loss using accurate semantic maps obtained by SAM 3, mitigating segmentation errors caused by cross-dataset label space discrepancies. Additionally, we develop a carefully designed low-light degradation model to synthesize training data and adopt a pre-training strategy, enabling the network to learn fine-grained semantic-aware brightness mappings. Based on these components, we develop a hybrid explicit–implicit semantic guidance framework. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in image quality, noise suppression, and structure preservation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan 430074, China.
ORCID-Profile: Binbing Liu
Zitieren
APA
Liang, Z., Huang, R., Ma, X., & Liu, B. (2026). Low-Light Image Enhancement Guided by Hybrid Explicit-Implicit Semantics. Sensors, 26(21), 7019. https://doi.org/10.3390/s26217019
Vancouver
Liang Z, Huang R, Ma X, Liu B. Low-Light Image Enhancement Guided by Hybrid Explicit-Implicit Semantics. Sensors. 2026;26(21):7019. doi:10.3390/s26217019
BibTeX
@article{Liang2026,
author = {Liang, Zanhao and Huang, Ruixiao and Ma, Xuhui and Liu, Binbing},
title = {Low-Light Image Enhancement Guided by Hybrid Explicit-Implicit Semantics},
journal = {Sensors},
year = {2026},
volume = {26},
number = {21},
pages = {7019},
doi = {10.3390/s26217019}
}
EUVIMED