Audio-driven talking face generation on OneMin-32
7.99ScVASA-1
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| VASA-1Training data scale=10% data2024.04 | 7.99 | 6.645 | 0.441 | 0.229 | 147.401 | |
| VASA-1Training data scale=Full data2024.04 | 7.957 | 6.635 | 0.465 | 0.316 | 105.88 | |
| Real video2024.04 | 7.192 | 7.254 | 0.559 | 0.405 | 29.25 | |
| Audio2Head2024.04 | 5.992 | 8.211 | 0.205 | 0.239 | 209.77 | |
| SadTalker2024.04 | 5.501 | 8.85 | 0.383 | 0.252 | 214.51 | |
| MakeItTalk2024.04 | -0.123 | 14.34 | 0.002 | 0.19 | 304.83 |