Text-to-Motion Generation on HumanML3D 19 (test)
0.0016FIDGround Truth
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Ground Truth2024.12 | 0.0016 | — | — | — | 2.96 | 9.62 | — | 80 | |
| Real motionground_truth=true2024.12 | 0.002 | 51.1 | 70.3 | 79.7 | 2.974 | 9.503 | — | — | |
| Real motion2024.12 | 0.002 | 51.1 | 70.3 | 79.7 | 2.974 | 9.503 | — | — | |
| Motion Anything2025.03 | 0.028 | 54.6 | 73.5 | 82.9 | 2.859 | 9.521 | 2.705 | — | |
| MoGenTS2025.03 | 0.033 | 52.9 | 71.9 | 81.2 | 2.867 | 9.57 | — | — | |
| LMM2025.03 | 0.04 | 52.5 | 71.9 | 81.1 | 2.943 | 9.814 | 2.683 | — | |
| MoMask2025.03 | 0.045 | 52.1 | 72 | 80.7 | 2.958 | — | 1.241 | — | |
| MCM2025.03 | 0.053 | 50.2 | 69.2 | 78.8 | 3.037 | 9.585 | 0.81 | — | |
| BAMM2025.03 | 0.055 | 52.5 | 71.3 | 81.4 | 2.919 | 9.717 | 1.687 | — | |
| BAD2025.03 | 0.065 | 51.7 | 71.3 | 80.8 | 2.901 | 9.694 | 1.194 | — | |
| MMM2025.03 | 0.072 | 50.4 | 70.6 | 80.2 | 2.998 | 9.411 | 1.164 | — | |
| DiverseMotion2025.03 | 0.08 | 51.5 | 69.6 | 79.4 | 2.941 | 9.683 | 1.869 | — | |
| ReMoDiffuse2025.03 | 0.103 | 51 | 69.8 | 79.5 | 2.974 | 9.018 | 1.795 | — | |
| ReMoDiffusionlatent diffusion model=false2024.12 | 0.103 | 51 | 69.8 | 79.5 | 2.974 | 9.278 | 1.795 | — | |
| ReMoDiffusion2024.12 | 0.103 | 51 | 69.8 | 79.5 | 2.974 | 9.018 | 1.795 | — | |
| GUESSlatent diffusion model=true2024.12 | 0.109 | 50.3 | 68.8 | 78.7 | 3.006 | 9.826 | 2.43 | — | |
| ENERGYMOGENrepresentation=skeleton2024.12 | 0.139 | 52.8 | 71.8 | 81 | 2.902 | 9.386 | 2.549 | — | |
| FineMoGenlatent diffusion model=false2024.12 | 0.151 | 50.4 | 69 | 78.4 | 2.998 | 9.268 | 2.696 | — | |
| FineMoGen2024.12 | 0.151 | 50.4 | 69 | 78.4 | 2.998 | 9.263 | 2.696 | — | |
| MotionCraft2025.03 | 0.173 | 50.1 | 69.7 | 79.6 | 3.025 | 9.543 | — | — | |
| ENERGYMOGEN (CompML)latent diffusion model=true2024.12 | 0.176 | 52.6 | 71.8 | 81.5 | 2.931 | 9.5 | 2.27 | — | |
| ENERGYMOGENlatent diffusion model=true2024.12 | 0.188 | 52.3 | 71.5 | 81.5 | 2.915 | 9.488 | 2.205 | — | |
| Fg-T2Mlatent diffusion model=false2024.12 | 0.243 | 49.2 | 68.3 | 78.3 | 3.109 | 9.926 | 1.614 | — | |
| MotionMambalatent diffusion model=true2024.12 | 0.281 | 50.2 | 69.3 | 79.2 | 3.06 | 9.871 | 2.294 | — | |
| M2DMlatent diffusion model=false2024.12 | 0.352 | 49.7 | 68.2 | 76.3 | 3.134 | 9.92 | 3.587 | — | |
| ReMoDiffusion2024.12 | 0.4 | — | — | — | 5.24 | 9.35 | — | 64 | |
| EnergyMoGen2024.12 | 0.43 | — | — | — | 5.22 | 9.52 | — | 67 | |
| FineMoGen2024.12 | 0.45 | — | — | — | 5.27 | 9.23 | — | 64 | |
| MLDlatent diffusion model=true2024.12 | 0.473 | 48.1 | 67.3 | 77.2 | 3.196 | 9.724 | 2.413 | — | |
| MDMlatent diffusion model=false2024.12 | 0.489 | 41.8 | 60.4 | 70.7 | 3.63 | 9.45 | 2.87 | — | |
| MDM2024.12 | 0.489 | 41.8 | 60.4 | 70.7 | 3.63 | 9.45 | 2.87 | — | |
| PriorMDMinference_mode=Double take2024.12 | 0.6 | — | — | — | 5.61 | 9.5 | — | 59 | |
| MotionDiffuselatent diffusion model=false2024.12 | 0.63 | 49.1 | 68.1 | 78.2 | 3.113 | 9.41 | 1.553 | — | |
| MotionDiffuse2024.12 | 0.63 | 49.1 | 68.1 | 78.2 | 3.113 | 9.41 | 1.553 | — | |
| PriorMDMinference_mode=First take2024.12 | 1 | — | — | — | 5.63 | 9.46 | — | 59 | |
| TM2D2025.03 | 1.021 | 31.9 | 50.3 | 58.9 | 4.098 | 9.513 | 4.139 | — | |
| MotionDiffuse2024.12 | 1.76 | — | — | — | 5.4 | 8.55 | — | 62 |