TalkVid
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Talking Head Generation | TalkVid self-driven 30 clips (held-out) | FVD87.85 | 16 | |
| Image-to-Video lip-syncing | TalkVid | FID55.38 | 12 | |
| Video-to-Video lip-syncing | TalkVid Self-Reenactment | FID35.51 | 9 | |
| Identity-Preserving Talking Head Generation | TalkVid | Speaker Similarity0.599 | 6 | |
| Video-to-Video lip-syncing | TalkVid Novel Audio | FID41.25 | 4 |
Showing 5 of 5 rows