AI Paper Atlas

Research map / Video / Video generation

Benchmarking Single-Factor Physical Video-to-Audio Generation

Tingle Li, Siddharth Gururani, Kevin J. Shih, Gantavya Bhatt, Sang-gil Lee, Zhifeng Kong, Arushi Goel, Gopala Anumanchipalli, Ming-Yu Liu

CVPR 2026 · Video › Video generation · approach: Video-to-audio synthesis · 1 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 text captions at inference (ablation)MMAudio · FlatSounds-Physicsphysical Confidence: 0.221 -> 0.226Mixed
add text captions at inference (ablation)MMAudio-Phys · FlatSounds-Physicsphysical Confidence: 0.289 -> 0.306Improved
add text captions at inference (ablation)FoleyCrafter · FlatSounds-Physicsphysical Confidence: 0.217 -> 0.205Hurt
add text captions at inference (ablation)ThinkSound · FlatSounds-Physicsphysical Confidence: 0.219 -> 0.228Improved
add text captions at inference (ablation)Hunyuan-V2A · FlatSounds-Physicsphysical Confidence: 0.296 -> 0.305Improved
add text captions at inference (ablation)Hunyuan-V2A · FlatSounds-SingleHit Coverage (%): 68.55 -> 65.21Hurt
add text captions at inference (ablation)MMAudio-Phys · FlatSounds-SingleHit Coverage (%): 56.46 -> 50.69Hurt
add text captions at inference (ablation)Hunyuan-V2A · FlatSounds-SingleTiming Error (ms): 44.34 -> 44.76Hurt
add text captions at inference (ablation)Hunyuan-V2A · VGGSoundDeSync: 0.326 -> 0.340Hurt
add text captions at inference (ablation)MMAudio-Phys · VGGSoundFAD-PASST: 66.31 -> 54.73Improved
add text captions at inference (ablation)Hunyuan-V2A · VGGSoundInception Score: 7.59 -> 15.29Improved
fine-tune MMAudio with physics-aware captions (MMAudio-Phys)MMAudio · FlatSounds-Physicsphysical Confidence: 0.226 -> 0.306Improved

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