AI Paper Atlas

Research map / Video / Video generation

Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance

Akio Hayakawa, Masato Ishii, Takashi Shibuya, Yuki Mitsufuji

ECCV 2026 · Video › Video generation · approach: Video-to-audio synthesis · 3 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
add Negative Audio Guidance (NAG)MMAudio-S-16k · Multi-Caps VGGSound individual tracksCLAP A-A separability: 79.75 -> 71.38Improved
use negative prompting instead of NAGMMAudio-S-16k · Multi-Caps VGGSound individual tracksIS: 12.47 -> 11.19Hurt
add NAG to step-by-step generation vs negative promptingMMAudio-S-16k · Multi-Caps VGGSound compositeFD_PANNs: 9.21 -> 6.47Improved
increase NAG coefficient beta from 0.0 to 2.0 (alpha 3.5) (ablation)MMAudio-S-16k + NAG · Multi-Caps VGGSound individual tracksCLAP A-A: 79.46 -> 71.97Improved
increase NAG coefficient beta from 0.0 to 2.0 (alpha 3.5) (ablation)MMAudio-S-16k + NAG · Multi-Caps VGGSound individual tracksIS: 12.27 -> 11.62Hurt
use descending (core event first) generation order instead of ascending (ablation)MMAudio-S-16k + NAG · Multi-Caps VGGSound compositeFD_PANNs: 7.36 -> 6.47Improved
use descending order instead of random order (ablation)MMAudio-S-16k + NAG · Multi-Caps VGGSound compositeFD_PANNs: 7.32 -> 6.47Improved
use step-by-step NAG instead of one-step generation plus AudioSepMMAudio-S-16k · Multi-Caps VGGSound individual tracksCLAP T-A: 23.42 -> 28.91Improved
use V2A NAG instead of independent T2A generation (AudioX)AudioX · Multi-Caps VGGSound compositeIB-score: 19.54 -> 28.65Improved
apply NAG to ControlFoleyControlFoley · ControlFoley individual tracksCLAP A-A: 60.67 -> 53.81Improved
apply NAG to MMAudioMMAudio-S-16k · AudioCaps testCLAP A-A: 68.89 -> 60.43Improved
apply NAG to MMAudioMMAudio-S-16k · Movie Gen Audio BenchCLAP A-A: 72.25 -> 66.32Improved

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