EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PRMEFNet: A Real-Time Unsupervised Multi-Exposure Fusion Network Driven by Prior Knowledge

Junwei Qi iD, Hangdong Wang iD, Xu Xiao iD, Jingpeng Gao iD

Journal of Imaging · 19.08.2026 · 12 (8) · 389

DOI: 10.3390/jimaging12080389 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 19.08.2026. Verfasst von Junwei Qi und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Heilongjiang Postdoctoral Fund, Heilongjiang Province Postdoctoral Science Foundation, China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Due to the limited dynamic range of imaging sensors, most cameras can only capture low-dynamic-range (LDR) images. Multi-exposure fusion (MEF) is an effective technique for generating high-dynamic-range (HDR) images. However, to simultaneously preserve texture details and global exposure, most existing methods primarily rely on more complex models to improve performance, resulting in higher computational costs and longer processing times. To address this issue, we propose a real-time unsupervised MEF network driven by prior knowledge. To this end, a hierarchical feature extraction module is designed that utilizes filtering operations to decompose the source images into base layers and detail layers. Features are extracted from each layer separately to reduce the difficulty of extracting effective features. Then, the receptive field of feature maps is expanded by dilated convolutions, and a window-based self-attention mechanism is applied to perform context modeling, achieving effective contextual modeling with low computational cost. Subsequently, texture features and global features are extracted separately to enable the model to maintain both local texture clarity and global smoothness. In addition, a one-dimensional lookup table is utilized to accelerate the inference process. Comprehensive experiments are conducted to verify the effectiveness of the proposed method. The subjective evaluation results demonstrate that the fused images exhibit superior visual quality, while objective experiments further quantify its superior performance, demonstrating that the proposed method effectively reduces computation time.

Schlagwörter

Stichwörter der Autor:innen

image decompositionmulti-exposure image fusionone-dimensional lookup tableprior knowledge guidanceunsupervised learning

Autor:innen und Institutionen

  • College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China.
  • Key Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information, Harbin 150001, China.

ORCID-Profile: Junwei Qi, Hangdong Wang, Xu Xiao, Jingpeng Gao

Förderung

  • Heilongjiang Postdoctoral Fund
  • Heilongjiang Province Postdoctoral Science Foundation, China

Zitieren

APA

Qi, J., Wang, H., Xiao, X., & Gao, J. (2026). PRMEFNet: A Real-Time Unsupervised Multi-Exposure Fusion Network Driven by Prior Knowledge. Journal of Imaging, 12(8), 389. https://doi.org/10.3390/jimaging12080389

Vancouver

Qi J, Wang H, Xiao X, Gao J. PRMEFNet: A Real-Time Unsupervised Multi-Exposure Fusion Network Driven by Prior Knowledge. Journal of Imaging. 2026;12(8):389. doi:10.3390/jimaging12080389

BibTeX
@article{Qi2026,
  author = {Qi, Junwei and Wang, Hangdong and Xiao, Xu and Gao, Jingpeng},
  title = {PRMEFNet: A Real-Time Unsupervised Multi-Exposure Fusion Network Driven by Prior Knowledge},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {8},
  pages = {389},
  doi = {10.3390/jimaging12080389}
}
Kostenlos starten →