TGFuse: An Infrared and Visible Image Fusion Approach Based on Transformer and Generative Adversarial Network

The end-to-end image fusion framework has achieved promising performance, with dedicated convolutional networks aggregating the multi-modal local appearance. However, long-range dependencies are directly neglected in existing CNN fusion approaches, impeding balancing the entire image-level perceptio...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing 2023-05, Vol.PP, p.1-1
Hauptverfasser:	Rao, Dongyu, Xu, Tianyang, Wu, Xiao-Jun
Format:	Artikel
Sprache:	eng
Schlagworte:	decision-level fusion Feature extraction Generative adversarial networks Image fusion RGBT tracking Task analysis temporal information Training Transformers visual object tracking Visualization
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!