Free-HeadGAN : Neural Talking Head Synthesis With Explicit Gaze Control

We present Free-HeadGAN, a person-generic neural talking head synthesis system. We show that modeling faces with sparse 3D facial landmarks is sufficient for achieving state-of-the-art generative performance, without relying on strong statistical priors of the face, such as 3D Morphable Models. Apar...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 8 vom: 28. Aug., Seite 9743-9756
1. Verfasser: Doukas, Michail Christos (VerfasserIn)
Weitere Verfasser: Ververas, Evangelos, Sharmanska, Viktoriia, Zafeiriou, Stefanos
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't