AI Paper Atlas

Research map / Video / Video generation

VAFlow: Video-to-Audio Generation with Cross-Modality Flow Matching

Xihua Wang, Xin Cheng, Yuyue Wang, Ruihua Song, Yunfeng Wang

ICCV 2025 · Video › Video generation · approach: Video-to-audio synthesis · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use video latent prior from alignment VAE without joint tuning instead of Gaussian prior (ablation)VAFlow-CLIP · VGGSound test (source distribution ablation)FD (PaSST): 102.6 -> 111.8Hurt
add joint tuning of alignment VAE encoder with the estimator (ablation)VAFlow-CLIP with video prior · VGGSound test (source distribution ablation)FD (PaSST): 111.8 -> 87.7Improved
jointly tuned video prior instead of Gaussian prior (ablation)VAFlow-CLIP · VGGSound test (source distribution ablation)IS (mel): 67.6 -> 73.6Improved
add cross-attention layers with explicit video conditioning (ablation)VAFlow-CLIP (no CFG) · VGGSound test (conditioning ablation)sync accuracy: 31.7 -> 78.0Improved
add cross-attention layers with explicit video conditioning (ablation)VAFlow-CLIP (no CFG) · VGGSound test (conditioning ablation)IB-VA: 8.5 -> 21.0Improved
zero out video input to cross-attention at inference (ablation)VAFlow-CLIP · VGGSound test (conditioning ablation)sync accuracy: 78.0 -> 18.9Hurt
add classifier-free guidance (ablation)VAFlow-CLIP with cross-attention · VGGSound test (conditioning ablation)FD (PaSST): 133.8 -> 87.7Improved
add classifier-free guidance (ablation)VAFlow-CLIP with cross-attention · VGGSound test (conditioning ablation)sync accuracy: 78.0 -> 88.1Improved
use CAVP features instead of CLIP features (ablation)VAFlow · VGGSound testsync accuracy: 88.1 -> 96.3Improved
use CAVP features instead of CLIP features (ablation)VAFlow · VGGSound testFD (PaSST): 87.7 -> 91.8Hurt
use VidTok reconstruction features instead of CLIP (ablation)VAFlow · VGGSound testFD (PaSST): 87.7 -> 128.5Hurt
use VidTok reconstruction features instead of CLIP (ablation)VAFlow · VGGSound testIB-VA: 28.6 -> 12.9Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy