UniSwap is a streaming audio-video diffusion model that transfers a reference face and voice onto a source talking video while keeping motion, scene, and speech content.
Out of time: Auto- mated lip sync in the wild
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UniSwap: Streaming Audio-Visual Identity Swapping for Talking Videos
UniSwap is a streaming audio-video diffusion model that transfers a reference face and voice onto a source talking video while keeping motion, scene, and speech content.