AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

How Far Can We Go With Synthetic Data for Audio-Visual Sound Source Localization?

Arda Senocak, Sooyoung Park, Tae-Hyun Oh, Joon Son Chung

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization

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
replace real VGGSound training data with fully synthetic data at the same scale (ablation)ACL-SSL · Single Source Localization (1x)cIoU: 48.03 -> 47.97No clear effect
replace real images with synthetic images, keep real audio (ablation)ACL-SSL · Single Source Localization (1x)cIoU: +7.10 cIoU, +4.94 cIoU Adap.Improved
replace real images with synthetic images, keep real audio (ablation)ACL-SSL · Interactive Localization (1x)IIoU: +10.40 IIoU, +10.91 IIoU Adap.Improved
replace real images with synthetic images, keep real audio (ablation)ACL-SSL · Audio-Visual Segmentation (1x)mIoU: +4.61 mIoU, +3.50 mIoU Adap.Improved
replace real audio with synthetic audio, keep real images (ablation)ACL-SSL · Single Source Localization (1x)cIoU: 48.03 -> 46.38Hurt
add 10K real audio to synthetic images and synthetic audio (ablation)ACL-SSL · Single Source Localization (1x)cIoU: +4.20 cIoU, +2.53 cIoU Adap. vs OriginalImproved
scale fully synthetic data to 2x (ablation)ACL-SSL · Single Source LocalizationcIoU: 47.11 (2x) vs 48.03 originalNo clear effect
scale fully synthetic data to 3x (ablation)ACL-SSL · Single Source LocalizationcIoU: +0.87 cIoU, -0.54 cIoU Adap. vs OriginalImproved
scale synthetic images with real audio from 1x to 3x (ablation)ACL-SSL · Single Source LocalizationcIoU: 55.13 -> 54.68 (2x) -> 55.73 (3x)Improved
add synthetic image-real audio pairs on top of full real VGGSound (3x)ACL-SSL · Single Source LocalizationcIoU: +8.62 cIoU, +7.00 cIoU Adap. vs OriginalImproved
add synthetic image-real audio pairs on top of full real VGGSound (3x)ACL-SSL · Interactive LocalizationIIoU: +12.16 IIoU, +13.35 IIoU Adap.Improved
add synthetic image-real audio pairs on top of full real VGGSound (3x)ACL-SSL · Audio-Visual SegmentationmIoU: +5.58 mIoU, +4.22 mIoU Adap.Improved

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