DTSGAN: Learning Dynamic Textures via Spatiotemporal Generative Adversarial Network

Dynamic texture synthesis aims to generate sequences that are visually similar to a reference video texture and exhibit specific stationary properties in time. In this paper, we introduce a spatiotemporal generative adversarial network (DTSGAN) that can learn from a single dynamic texture by capturi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Li, Xiangtian, Wang, Xiaobo, Qi, Zhen, Cao, Han, Zhang, Zhaoyang, Xiang, Ao
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!