Metric: FD (higher is better)
| # | Model↕ | FD▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | V2A-Mapper | 24.168 | No | V2A-Mapper: A Lightweight Solution for Vision-to... | 2023-08-18 | Code |
| 2 | ReWas | 15.24 | No | Read, Watch and Scream! Sound Generation from Te... | 2024-07-08 | Code |
| 3 | Frieren | 12.26 | No | Frieren: Efficient Video-to-Audio Generation Net... | 2024-06-01 | Code |
| 4 | MMAudio-S-16kHz | 5.22 | No | MMAudio: Taming Multimodal Joint Training for Hi... | 2024-12-19 | Code |
| 5 | MMAudio-L-44.1kHz | 4.72 | No | MMAudio: Taming Multimodal Joint Training for Hi... | 2024-12-19 | Code |