Multi-scale diffusion model for underwater image restoration and enhancement
PLOS One · 2025
DOI: 10.1371/journal.pone.0331465 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Yuan Fang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Innovation and Entrepreneurship, Dalian Polytechnic University, Dalian, Liaoning, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Image Enhancement, Models, Theoretical. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific Research Fund of Liaoning Provincial Education Department, Natural Science Foundation of Liaoning Province.
Abstract (Originalsprache)
Background
Underwater environments face challenges with image degradation due to light absorption and scattering, resulting in blurring, reduced contrast, and color distortion. This significantly impacts underwater exploration and environmental monitoring, necessitating advanced algorithms for effective enhancement.
Objectives
The study aims to develop an innovative underwater image enhancement algorithm that integrates physical models with deep learning to improve visual quality and surpass existing methods in performance metrics.
Methods
The proposed method employs a multi-level design combining physical insights from the diffusion model with deep learning. It utilizes an encoder-decoder pipeline for image decomposition, adaptive color adjustment through a color encoder network, and pixel optimization using an inverse denoising diffusion model to achieve enhanced visual quality. Results and conclusion: Experimental results demonstrate significant improvements, with an average increase of 6.61 in PSNR, 0.15 in SSIM, and 0.87 in UIQM. The integration of physical models and deep learning proves effective for underwater image enhancement. This research advances the field by providing a robust framework for addressing imaging challenges in underwater environments.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Innovation and Entrepreneurship, Dalian Polytechnic University, Dalian, Liaoning, China.
- School of Information Science and Engineering, Dalian Polytechnic University, Dalian, Liaoning, China.
- The Institute of Port Information Digitalization, China Liaoning Port Group Co. Ltd., Dalian, Liaoning, China.
ORCID-Profile: Yuan Fang
Förderung
- Scientific Research Fund of Liaoning Provincial Education Department
- Natural Science Foundation of Liaoning Province
Zitieren
APA
Fang, Y., Li, Q., & Wang, K. (2025). Multi-scale diffusion model for underwater image restoration and enhancement. PLOS One. https://doi.org/10.1371/journal.pone.0331465
Vancouver
Fang Y, Li Q, Wang K. Multi-scale diffusion model for underwater image restoration and enhancement. PLOS One. 2025. doi:10.1371/journal.pone.0331465
BibTeX
@article{Fang2025,
author = {Fang, Yuan and Li, Qianyi and Wang, Kai},
title = {Multi-scale diffusion model for underwater image restoration and enhancement},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0331465}
}
EUVIMED