Motion2Language on Open3DFaceVid
4.02CorELanguage2Motion
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Language2MotionInput Space=Geometry Tokens2026.03 | 4.02 | 3.35 | 3.63 | 4.29 | 3.79 | — | — | — | — | — | |
| Gemini2.5 VLMInput Space=Pixels2026.03 | 2.45 | 2.91 | 3.51 | 2.88 | 3.41 | — | — | — | — | — | |
| HumanOmniInput Space=Pixels2026.03 | 1.84 | 1.17 | 1.09 | 2.04 | 1 | — | — | — | — | — | |
| Gemini2.5 VLMInput type=natural images2026.03 | — | — | — | — | — | 4.21 | 3.17 | 3.92 | 4.17 | 3.82 | |
| HumanOmniInput type=natural images2026.03 | — | — | — | — | — | 3.66 | 1.59 | 1.42 | 3.82 | 1.27 | |
| OursInput type=natural images2026.03 | — | — | — | — | — | 4.02 | 3.35 | 3.63 | 4.29 | 3.79 |