Real-Time, High-Fidelity Face Identity Swapping With a Vision Foundation Model

Many recent face-swapping methods based on generative adversarial networks (GANs) or autoencoders achieve strong performance under constrained conditions but degrade significantly in high-resolution or extreme pose scenarios. Moreover, most existing models generate outputs at limited resolutions (<i...

Descripció completa

Dades bibliogràfiques

Autors principals:	Jongmin Yu, Hyeontaek Oh, Zhongtian Sun, Younkwan Lee, Jinhong Yang
Format:	Artigo
Idioma:	Inglês
Publicat:	IEEE 2025-01-01
Col·lecció:	IEEE Access
Matèries:	Face identity swap face swap vision foundation model contrastive learning
Accés en línia:	https://ieeexplore.ieee.org/document/11152011/
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!