Speech-driven video generation on HDTF 66 (test)
5.779FIDArchon
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Archontrained on the benchmark dataset=false2026.05 | 5.779 | 81.64 | 6.198 | 8.822 | 3.94 | |
| Hallo3trained on the benchmark dataset=true2026.05 | 12.78 | 96.51 | 6.376 | 9.131 | 3.83 | |
| AniPortraittrained on the benchmark dataset=false2026.05 | 42.03 | 162.8 | 2.879 | 10.889 | 3.813 | |
| EchoMimictrained on the benchmark dataset=true2026.05 | 45.9 | 241.6 | 5.467 | 9.36 | 3.743 |