| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TikTok | StableAnimator | FVD140.62 | 15 | 1mo ago | |
| Unseen100 | StableAnimator | L1 Loss27,100 | 9 | 1mo ago | |
| TikTok dataset 14 (test) | MagicAnimate | L1 Loss0.0003 | 8 | 1mo ago | |
| TED-talks (test) | TPS | AKD2.16 | 8 | 1mo ago | |
| User Study 30 selected videos | StableAnimator | M-A95.6 | 7 | 1mo ago | |
| HyperMotionX Bench | Hypermotion | PSNR22.03 | 6 | 1mo ago | |
| User Study 50 participants 5-point Mean Opinion Score | Position Shift Adaptive Module | VC Score4 | 5 | 1mo ago | |
| Our dataset (test) | Position Shift Adaptive Module | Subject Consistency92.54 | 5 | 1mo ago | |
| TikTok and internet videos (test) | MTVCrafter | SSIM0.7489 | 5 | 1mo ago | |
| In-the-wild cross-driving (test) | X-Dyna | DTFVD5.923 | 5 | 1mo ago | |
| TikTok (test) | Position Shift Adaptive Module | Subject Consistency95.56 | 5 | 1mo ago | |
| Single-character benchmark | EverybodyDance | SSIM0.772 | 4 | 1mo ago | |
| Multi-character benchmark | EverybodyDance | SSIM0.671 | 4 | 1mo ago |
