AI Paper Atlas

Research map / Video / Video generation

CAFA: a Controllable Automatic Foley Artist

Roi Benita, Michael Finkelson, Tavi Halperin, Gleb Sterkin, Yossi Adi

ICCV 2025 · Video › Video generation · approach: Video-to-audio synthesis · 4 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 CLIP visual features alongside AV-CLIP (ablation)CAFA · VGGSound testFAD / DeSync: FAD 12.60 -> 14.44; DeSync 0.96 -> 1.02No clear effect
add fine-tuning on VisualSound after VGGSound training (ablation)CAFA-B · VGGSound testIS / DeSync: IS 11.84 -> 13.45; DeSync 1.00 -> 0.96Improved
swap Stable-Audio-Open for TangoFlux as T2A backbone (ablation)CAFA · VGGSound testFAD: FAD 12.60 -> 19.94; IS 13.45 -> 16.94Mixed
use asymmetric CFG scale between 0.5 and 1 (ablation)CAFA · VGGSound-Sparseoverall trade-offImproved
add text conditioning to MMAudioMMAudio · VGGSound testFADHurt
use CAFA instead of MMAudio when text conflicts with videotext-video-to-audio · VGGSound-Sparse conflicting captionsAcc: 0.36 -> 0.87Improved
use CAFA instead of MMAudio when text aligns with videotext-video-to-audio · VGGSound testFAD: 6.89 -> 12.60Hurt
adapter-based training on frozen T2A model instead of full trainingCAFA · training costGPU hours: 304 -> ~48Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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