Few-shot Image Generation via Information Transfer from the Built Geodesic Surface

Images generated by most of generative models trained with limited data often exhibit deficiencies in either fidelity, diversity, or both. One effective solution to address the limitation is few-shot generative model adaption. However, the type of approaches typically rely on a large-scale pre-train...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-03
Hauptverfasser:	Han, Yuexing, Ruan, Liheng, Wang, Bing
Format:	Artikel
Sprache:	eng
Schlagworte:	Datasets Image enhancement Image processing Image quality Information transfer Interpolation Modules Regularization Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!