EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Underwater Image Enhancement Using a Diffusion Model with Adversarial Learning

Xueyan Ding iD, Xiyu Chen, Yixin Sui, Yafei Wang, Jianxin Zhang iD

Journal of Imaging · 27.06.2025 · 11 (7) · 212

DOI: 10.3390/jimaging11070212 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 27.06.2025. Verfasst von Xueyan Ding und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Dalian Minzu University, Dalian 116600, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Dalian Youth Science and Technology Star Project, National Natural Science Foundation of China, Liaoning Doctoral Research Start-up Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Due to the distinctive attributes of underwater environments, underwater images frequently encounter challenges such as low contrast, color distortion, and noise. Current underwater image enhancement techniques often suffer from limited generalization, preventing them from effectively adapting to a variety of underwater images taken in different underwater environments. To address these issues, we introduce a diffusion model-based underwater image enhancement method using an adversarial learning strategy, referred to as adversarial learning diffusion underwater image enhancement (ALDiff-UIE). The generator systematically eliminates noise through a diffusion model, progressively aligning the distribution of the degraded underwater image with that of a clear underwater image, while the discriminator helps the generator produce clear, high-quality underwater images by identifying discrepancies and pushing the generator to refine its outputs. Moreover, we propose a multi-scale dynamic-windowed attention mechanism to effectively fuse global and local features, optimizing the process of capturing and integrating information. Qualitative and quantitative experiments on four benchmark datasets—UIEB, U45, SUIM, and LSUI—demonstrate that ALDiff-UIE increases the average PCQI by approximately 12.8% and UIQM by about 15.6%. The results indicate that our method outperforms several mainstream approaches in terms of both visual quality and quantitative metrics, showcasing its effectiveness in enhancing underwater images.

Schlagwörter

Stichwörter der Autor:innen

adversarial learningattention mechanismdiffusion modelunderwater image enhancement

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Dalian Minzu University, Dalian 116600, China.
  • Research Center of Multimodal Information Perception and Intelligent Processing, Dalian Minzu University, Dalian 116600, China.
  • School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China.

ORCID-Profile: Xueyan Ding, Jianxin Zhang

Förderung

  • Dalian Youth Science and Technology Star Project
  • National Natural Science Foundation of China
  • Liaoning Doctoral Research Start-up Fund
  • Liaoning Basic Research Project

Zitieren

APA

Ding, X., Chen, X., Sui, Y., Wang, Y., & Zhang, J. (2025). Underwater Image Enhancement Using a Diffusion Model with Adversarial Learning. Journal of Imaging, 11(7), 212. https://doi.org/10.3390/jimaging11070212

Vancouver

Ding X, Chen X, Sui Y, Wang Y, Zhang J. Underwater Image Enhancement Using a Diffusion Model with Adversarial Learning. Journal of Imaging. 2025;11(7):212. doi:10.3390/jimaging11070212

BibTeX
@article{Ding2025,
  author = {Ding, Xueyan and Chen, Xiyu and Sui, Yixin and Wang, Yafei and Zhang, Jianxin},
  title = {Underwater Image Enhancement Using a Diffusion Model with Adversarial Learning},
  journal = {Journal of Imaging},
  year = {2025},
  volume = {11},
  number = {7},
  pages = {212},
  doi = {10.3390/jimaging11070212}
}
Kostenlos starten →