EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSSA-Net: Multi-Modal Structural and Semantic-Adaptive Network for Low-Light Image Enhancement

Tianxiang Chen, Xiaoyi Wang iD, Tongshun Zhang iD, Qiuzhan Zhou

Sensors · 25.03.2026 · 26 (7) · 2059

DOI: 10.3390/s26072059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.03.2026. Verfasst von Tianxiang Chen und 3 weiteren Autor:innen. Beteiligte Einrichtung: Samueli School of Engineering, University of California, Los Angeles, CA 90095, USA. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low-light image enhancement (LLIE) remains challenging due to severe degradation of high-frequency structures and semantic ambiguity under extreme darkness. Although existing methods achieve satisfactory brightness recovery, they often suffer from structural inconsistency and semantic drift, as diverse scenes are typically processed with uniform enhancement strategies or static text prompts. To address these issues, we propose a Multi-Modal Structural and Semantic-Adaptive Network (MSSA-Net) under a structure-anchored paradigm. First, we design a Multi-Scale Self-Refinement Block (MSRB) to enhance degraded visible representations through multi-scale feature extraction and progressive refinement. Meanwhile, a pseudo-infrared structural prior derived from the input image is introduced to provide noise-insensitive geometric cues. These cues are extracted via a Structure-Guided Cross-Attention (SGCA) module to produce structure-dominant features. The refined visible features and structural features are then adaptively integrated through an adaptive residual fusion (ARF) module to achieve balanced restoration. Furthermore, we develop a Large Multi-modal Model (LMM)-Driven Scene-Adaptive Attention mechanism that generates instance-aware scene tags from a coarse preview and injects semantic embeddings into visual features. Extensive experiments demonstrate that MSSA-Net improves structural fidelity, brightness recovery, and semantic naturalness across multiple benchmarks.

Schlagwörter

Stichwörter der Autor:innen

image sensor restorationlow-light enhancementvision transformer

Autor:innen und Institutionen

  • Samueli School of Engineering, University of California, Los Angeles, CA 90095, USA.
  • College of Computer Science and Technology, Jilin University, Changchun 130012, China.
  • College of Communication Engineering, Jilin University, Changchun 130012, China.

ORCID-Profile: Xiaoyi Wang, Tongshun Zhang

Zitieren

APA

Chen, T., Wang, X., Zhang, T., & Zhou, Q. (2026). MSSA-Net: Multi-Modal Structural and Semantic-Adaptive Network for Low-Light Image Enhancement. Sensors, 26(7), 2059. https://doi.org/10.3390/s26072059

Vancouver

Chen T, Wang X, Zhang T, Zhou Q. MSSA-Net: Multi-Modal Structural and Semantic-Adaptive Network for Low-Light Image Enhancement. Sensors. 2026;26(7):2059. doi:10.3390/s26072059

BibTeX
@article{Chen2026,
  author = {Chen, Tianxiang and Wang, Xiaoyi and Zhang, Tongshun and Zhou, Qiuzhan},
  title = {MSSA-Net: Multi-Modal Structural and Semantic-Adaptive Network for Low-Light Image Enhancement},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {7},
  pages = {2059},
  doi = {10.3390/s26072059}
}
Kostenlos starten →