Decoupled two-stage talking head generation via Gaussian-landmark-based neural radiance fields

Talking head generation based on neural radiance fields (NeRF) has gained prominence, primarily owing to its implicit 3D representation capability within neural networks. However, most NeRF-based methods often intertwine audio-to-video conversion in a joint training process, resulting in challenges...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Boyao Ma, Yuanping Cao, Lei Zhang
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	Tsinghua University Press 2025-08-01
Σειρά:	Computational Visual Media
Θέματα:	audio-driven generation talking head transformer neural radiance fields (nerf) rendering
Διαθέσιμο Online:	https://www.sciopen.com/article/10.26599/CVM.2025.9450482
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!