SeamsTalk: Seamless Talking Face Generation via Flow-Guided Inpainting

Talking face generation aims to generate a face video to speak according to a given audio or driving video. Despite the importance of natural lower face movement, previous approaches have focused only on animating the lip, neglecting the connection between the modified lower face and the original ba...

Descrición completa

Detalles Bibliográficos

Principais autores:	Yeongho Jeong, Gyeongman Kim, Doohyuk Jang, Jaeryong Hwang, Eunho Yang
Formato:	Artigo
Idioma:	Inglês
Publicado:	IEEE 2024-01-01
Series:	IEEE Access
Assuntos:	Computer vision face reenactment talking face generation video inpainting
Acceso en liña:	https://ieeexplore.ieee.org/document/10479466/
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!