Frieren: Efficient Video-to-Audio Generation with Rectified Flow
Matching
Frieren: Efficient Video-to-Audio Generation with Rectified Flow
Matching
Video-to-audio (V2A) generation aims to synthesize content-matching audio from silent video, and it remains challenging to build V2A models with high generation quality, efficiency, and visual-audio temporal synchrony. We propose Frieren, a V2A model based on rectified flow matching. Frieren regresses the conditional transport vector field from noise to spectrogram …