Semi-Supervised Single-Image Dehazing Network via Disentangled Meta-Knowledge

Captured outdoor scene images are easily affected by haze. Most image dehazing methods have limited generalization capabilities for real-world hazy images owing to the complexities of real-world environments and domain gaps in the training datasets. This article proposes a semi-supervised single-ima...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on multimedia 2024, Vol.26, p.2634-2647
Hauptverfasser:	Jia, Tongyao, Li, Jiafeng, Zhuo, Li, Yu, Tianjian
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Atmospheric modeling Datasets Disentangled representations Image reconstruction meta-learning Metalearning Prediction algorithms semi-supervised learning single-image dehazing Synthetic data Task analysis Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!