Motion In-between on Motion-X
0.009FIDReal
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Real2024.05 | 0.009 | 2.316 | — | |
| Ground Truth2024.05 | 0.009 | 2.316 | — | |
| M³GPTStrategy=Pre-trained2024.05 | 0.604 | 1.879 | — | |
| M3GPTstage=pretrain2024.05 | 0.604 | 1.897 | 5.692 | |
| M³GPT (Pre-trained)Training Strategy=Pre-trained, Hardware Platform=Ascend 910B NPU2024.05 | 0.608 | 1.874 | — | |
| M³GPTStrategy=Instruction-tuned2024.05 | 0.612 | 1.9 | — | |
| M3GPTstage=finetune2024.05 | 0.612 | 1.9 | 5.649 | |
| M³GPT (Instruction-tuned)Training Strategy=Instruction-tuned, Hardware Platform=Ascend 910B NPU2024.05 | 0.621 | 1.903 | — | |
| MoMask2024.05 | 0.626 | 1.884 | — | |
| MotionGPT2024.05 | 0.648 | 1.875 | — | |
| Trained single taskStrategy=Single Task Training2024.05 | 0.692 | 1.81 | — | |
| Trained single task2024.05 | 0.692 | 1.81 | 6.69 | |
| Trained single taskTraining Strategy=single task training, Hardware Platform=Ascend 910B NPU2024.05 | 0.712 | 1.88 | — | |
| MDM2024.05 | 0.831 | 1.768 | — | |
| MDM2024.05 | 0.831 | 1.768 | 6.542 |