AI Paper Atlas

Research map / Video / Video generation

Omni2Sound: Towards Unified Video-Text-to-Audio Generation

Yusheng Dai, Zehua Chen, Yuxuan Jiang, Qiuhong Ke, Jianfei Cai, Jun Zhu

CVPR 2026 · Video › Video generation · approach: Video-to-audio synthesis · 13 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
raise T2A sampling ratio from 0.20 to 0.40 without VT2A data (ablation)Omni2Sound Stage 2 · VGGSound-Omni T2AFAD: 1.36 -> 1.06Improved
raise T2A sampling ratio from 0.20 to 0.40 without VT2A data (ablation)Omni2Sound Stage 2 · VGGSound-Omni V2AFAD: 0.56 -> 0.62Hurt
add high-alignment SoundAtlas VT2A data as bridge (ablation)Omni2Sound Stage 2 · VGGSound-Omni T2AFAD: 1.06 -> 0.94Improved
use SoundAtlas captions instead of audio-only Gemini 2.5 captions (ablation)Omni2Sound Stage 2 · VGGSound-Omni T2AFAD: 1.13 -> 0.94Improved
add Stage 1 T2A pretraining (ablation)Omni2Sound · VGGSound-Omni T2AFAD: 1.22 -> 0.94Improved
add Stage 1 T2A pretraining (ablation)Omni2Sound · VGGSound-Omni V2AFAD: 0.68 -> 0.57Improved
add decoupled Stage 3 robustness training after Stage 2 (ablation)Omni2Sound · VGGSound-Omni V2AFAD: 0.57 -> 0.51Improved
add decoupled Stage 3 robustness training after Stage 2 (ablation)Omni2Sound · VGGSound-Omni V2ADS: 0.49 -> 0.47Improved
merge Stage 3 into Stage 2 instead of decoupling (ablation)Omni2Sound · VGGSound-Omni V2AFAD: 0.51 -> 0.60Hurt
add Stage 3 off-screen synthesis (ablation)Omni2Sound · VGGSound-Omni off-screen VT2AFAD: 0.97 -> 0.85Improved
add Stage 3 off-screen synthesis (ablation)Omni2Sound · VGGSound-Omni off-screen VT2ALA-CLAP: 0.31 -> 0.32Improved
use Video-LLaMA captions instead of SoundAtlas-style captions at test timeOmni2Sound · VGGSound-Omni VT2AFAD: 0.53 -> 0.66Hurt

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