HDTF
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Talking Head Generation | HDTF (test) | FID1.86 | 49 | |
| Talking Head Generation | HDTF | FID8.31 | 33 | |
| Self-reenactment | HDTF | PSNR28.83 | 29 | |
| Talking Face Generation | HDTF (test) | SSIM1 | 16 | |
| Cross Reenactment | HDTF | CSIM90.3 | 15 | |
| Video-driven Talking Head Generation (Self-Reenactment) | HDTF | FID18.12 | 12 | |
| Visual Dubbing | HDTF (test) | PSNR34.425 | 9 | |
| Audio Driven Talking Head Generation | HDTF 51 (test) | SSIM1 | 9 | |
| Audio-driven Video Generation | HDTF | FID7.07 | 8 | |
| Lip Synchronization | HDTF | FID7.623 | 8 | |
| Audio-visual Synchronization | HDTF cross-driven | Sync-C (Cross-Gender)2.335 | 8 | |
| Self-reenactment | HDTF (test) | LPIPS0.143 | 8 | |
| Cross-identity Reenactment | HDTF 55 (test) | CSIM0.9004 | 8 | |
| Self-reenactment | HDTF 55 (test) | PSNR26.61 | 8 | |
| Talking head video generation | HDTF | FID14.76 | 8 | |
| Talking Face Generation | HDTF one-shot | FID21.362 | 7 | |
| Head avatar reconstruction | HDTF Dataset | PSNR27.99 | 7 | |
| Lip-Syncing | HDTF | FID8.42 | 7 | |
| Video-driven Talking Head Generation (Cross-Reenactment) | HDTF | FID27.85 | 7 | |
| Audio-driven talking face generation | HDTF (randomly sampled 50 videos) | FID9.084 | 6 | |
| Cross-identity Reenactment | HDTF | FVD107.9 | 6 | |
| Talking Head Synthesis | HDTF (test) | IQA3.994 | 6 | |
| Portrait image animation | HDTF | Sync-C8.094 | 6 | |
| Portrait relighting | HDTF | LE0.738 | 6 | |
| Portrait Image Animation | HDTF (test) | FID28.605 | 6 |
Showing 25 of 36 rows