Image Comes Dancing With Collaborative Parsing-Flow Video Synthesis

Transferring human motion from a source to a target person poses great potential in computer vision and graphics applications. A crucial step is to manipulate sequential future motion while retaining the appearance characteristic. Previous work has either relied on crafted 3D human models or trained...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on image processing 2021, Vol.30, p.9259-9269
Hauptverfasser:	Wu, Bowen, Xie, Zhenyu, Liang, Xiaodan, Xiao, Yubei, Dong, Haoye, Lin, Liang
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Collaboration Computer vision Frames (data processing) Generative adversarial networks generative model Human motion Humans Image resolution Motion Motion transfer Solid modeling Source code Synthesis Task analysis Three dimensional models Three-dimensional displays Training data Video video synthesis
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!