EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Degradation-Aware Multi-Stage Fusion for Underwater Image Enhancement

Lian Xie iD, Hao Chen, Jin Shu

Journal of Imaging · 08.01.2026 · 12 (1) · 37

DOI: 10.3390/jimaging12010037 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 08.01.2026. Verfasst von Lian Xie und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Civil Engineering, Hunan City University, Yiyang 413000, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hunan Province, Research Project of the Education Department of Hunan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Underwater images frequently suffer from color casts, low illumination, and blur due to wavelength-dependent absorption and scattering. We present a practical two-stage, modular, and degradation-aware framework designed for real-time enhancement, prioritizing deployability on edge devices. Stage I employs a lightweight CNN to classify inputs into three dominant degradation classes (color cast, low light, blur) with 91.85% accuracy on an EUVP subset. Stage II applies three scene-specific lightweight enhancement pipelines and fuses their outputs using two alternative learnable modules: a global Linear Fusion and a LiteUNetFusion (spatially adaptive weighting with optional residual correction). Compared to the three single-scene optimizers (average PSNR = 19.0 dB; mean UCIQE ≈ 0.597; mean UIQM ≈ 2.07), the Linear Fusion improves PSNR by +2.6 dB on average and yields roughly +20.7% in UCIQE and +21.0% in UIQM, while maintaining low latency (~90 ms per 640 × 480 frame on an Intel i5-13400F (Intel Corporation, Santa Clara, CA, USA). The LiteUNetFusion further refines results: it raises PSNR by +1.5 dB over the Linear model (23.1 vs. 21.6 dB), brings modest perceptual gains (UCIQE from 0.72 to 0.74, UIQM 2.5 to 2.8) at a runtime of ≈125 ms per 640 × 480 frame, and better preserves local texture and color consistency in mixed-degradation scenes. We release implementation details for reproducibility and discuss limitations (e.g., occasional blur/noise amplification and domain generalization) together with future directions.

Schlagwörter

Stichwörter der Autor:innen

UNetadaptive fusion networkdegradation-aware classificationmulti-stage fusionscene-specific enhancementunderwater image enhancement

Autor:innen und Institutionen

  • School of Civil Engineering, Hunan City University, Yiyang 413000, China.
  • School of Architecture and Traffic Engineering, Guilin University of Electronic Science and Technology, Guilin 541004, China.

ORCID-Profile: Lian Xie

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Hunan Province
  • Research Project of the Education Department of Hunan Province

Zitieren

APA

Xie, L., Chen, H., & Shu, J. (2026). Degradation-Aware Multi-Stage Fusion for Underwater Image Enhancement. Journal of Imaging, 12(1), 37. https://doi.org/10.3390/jimaging12010037

Vancouver

Xie L, Chen H, Shu J. Degradation-Aware Multi-Stage Fusion for Underwater Image Enhancement. Journal of Imaging. 2026;12(1):37. doi:10.3390/jimaging12010037

BibTeX
@article{Xie2026,
  author = {Xie, Lian and Chen, Hao and Shu, Jin},
  title = {Degradation-Aware Multi-Stage Fusion for Underwater Image Enhancement},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {1},
  pages = {37},
  doi = {10.3390/jimaging12010037}
}
Kostenlos starten →