Back to Search Start Over

Frieren: Efficient Video-to-Audio Generation with Rectified Flow Matching

Authors :
Wang, Yongqi
Guo, Wenxiang
Huang, Rongjie
Huang, Jiawei
Wang, Zehan
You, Fuming
Li, Ruiqi
Zhao, Zhou
Wang, Yongqi
Guo, Wenxiang
Huang, Rongjie
Huang, Jiawei
Wang, Zehan
You, Fuming
Li, Ruiqi
Zhao, Zhou
Publication Year :
2024

Abstract

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 latent with straight paths and conducts sampling by solving ODE, outperforming autoregressive and score-based models in terms of audio quality. By employing a non-autoregressive vector field estimator based on a feed-forward transformer and channel-level cross-modal feature fusion with strong temporal alignment, our model generates audio that is highly synchronized with the input video. Furthermore, through reflow and one-step distillation with guided vector field, our model can generate decent audio in a few, or even only one sampling step. Experiments indicate that Frieren achieves state-of-the-art performance in both generation quality and temporal alignment on VGGSound, with alignment accuracy reaching 97.22%, and 6.2% improvement in inception score over the strong diffusion-based baseline. Audio samples are available at http://frieren-v2a.github.io .

Details

Database :
OAIster
Publication Type :
Electronic Resource
Accession number :
edsoai.on1438563873
Document Type :
Electronic Resource