EdiDub treats visual dubbing as content-aware video editing: a diffusion model is conditioned on the original video and inverted latents preserve context while re-synchronizing lips to new speech.
Diffused heads: Diffusion models beat GANs on talking-face generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Video Editing for Audio-Visual Dubbing
EdiDub treats visual dubbing as content-aware video editing: a diffusion model is conditioned on the original video and inverted latents preserve context while re-synchronizing lips to new speech.