Video-to-audio generation on Greatest Hits
23.94AccuracyCondFoleyGen
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| CondFoleyGenInput modalities=reference audio and video2024.07 | 23.94 | 60.24 | 0.152 | |
| ReWaSInput modalities=material types as text prompts2024.07 | 19.15 | 63.28 | 0.1398 |