PROCESSING FRAMEWORK FOR TEMPORAL-CONSISTENT FACE MANIPULATION IN VIDEOS

Embodiments are disclosed for generating temporally consistent manipulated videos. A method of generating temporally consistent manipulated videos comprises receiving a target appearance and an input digital video including a plurality of frames, generating a plurality of target appearance frames fr...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	HUYNH THIEN, Nicolas, MISRAA, Aashish, GARG, Kshitiz, GUO, Han, AMINIAN, Ali, MARINO, William
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Embodiments are disclosed for generating temporally consistent manipulated videos. A method of generating temporally consistent manipulated videos comprises receiving a target appearance and an input digital video including a plurality of frames, generating a plurality of target appearance frames from the plurality of frames, training a video prediction network to generate a digital video wherein a subject of the digital video has its appearance modified to match the target appearance, providing the input digital video to the video prediction network, and generating, by the video prediction network, an output digital video wherein the subject of the output digital video has its appearance modified to match the target appearance.