Video To Sound Generation On Vgg Sound
평가 지표
FAD
FD
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | FAD | FD |
|---|---|---|
| read-watch-and-scream-sound-generation-from | 2.16 | 15.24 |
| frieren-efficient-video-to-audio-generation | 1.32 | 12.26 |
| taming-multimodal-joint-training-for-high | 0.79 | 5.22 |
| masked-generative-video-to-audio-transformers | 2.04 | - |
| taming-multimodal-joint-training-for-high | 0.97 | 4.72 |
| temporally-aligned-audio-for-video-with | 1.92 | - |
| v2a-mapper-a-lightweight-solution-for-vision | 0.841 | 24.168 |
| tell-what-you-hear-from-what-you-see-video-to | 2.38 | - |