Style Transfer of Thangka Images Highlighting Style Attributes

The HAA-GAN (Highlighting Artistic Attributes Generative Adversarial Net-work) style migration model is proposed to address the problem of poor expression of image artistic attributes and mismatch between semantic and stylistic features in images generated from Tangka image style transfer experiment...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE access 2023, Vol.11, p.104817-104829
Hauptverfasser:	Hu, Wenjin, Song, Huafei, Zhang, Fujun, Zhao, Yinqiu, Shi, Xinyue
Format:	Artikel
Sprache:	eng
Schlagworte:	Codec Coders Datasets Decoding Feature extraction Generators Image color analysis Image quality Matching multiscale discriminative network self-attention semantic information matching Semantics style transfer Thangka image Visual discrimination Visual effects wavelet multilevel transform Wavelet transforms
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!