Text-to-motion generation on KIT-ML (test)
0.002FIDReal motion
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Real motionGround truth motion length=True2024.06 | 0.002 | 51.38 | 69.57 | 79.37 | 2.974 | — | — | — | — | |
| Real motionFramework=null2024.06 | 0.002 | 51.38 | 69.57 | 79.37 | 2.974 | — | — | — | — | |
| Ground Truth2025.12 | 0.031 | 42.4 | 64.9 | 77.9 | 2.788 | 11.08 | — | — | — | |
| Real MotionEditable=-2025.12 | 0.031 | 42.4 | 64.9 | 77.9 | 2.788 | 11.08 | — | — | — | |
| RealText Encoder=-2025.12 | 0.031 | 42.4 | 64.9 | 77.9 | 2.788 | 11.08 | — | — | — | |
| Real Motions2026.02 | 0.031 | 42.4 | 64.9 | 77.9 | 2.788 | 11.08 | — | — | — | |
| RealYear=–2026.02 | 0.031 | 42.4 | 64.9 | 77.9 | 2.788 | 11.08 | — | — | — | |
| Real motion2026.03 | 0.031 | 42.4 | 64.9 | 77.9 | 2.788 | 11.08 | — | — | — | |
| Real data2026.03 | 0.031 | 42.4 | 64.9 | 77.9 | 2.788 | 11.08 | — | — | — | |
| Real Motion2026.03 | 0.031 | 42.4 | 64.9 | 77.9 | 2.788 | 11.08 | — | — | — | |
| Real MotionStructure=-2026.04 | 0.031 | 42.4 | 64.9 | 77.9 | 2.788 | 11.08 | — | — | — | |
| Real motions2026.05 | 0.031 | 42.4 | 64.9 | 77.9 | 2.788 | 11.08 | — | — | — | |
| PGR²MOperation mode=Reconstruction, Editable=Yes, Transformer configuration=Base and Refine Transformers2025.12 | 0.083 | 41.5 | 63.9 | 77.1 | 2.824 | 10.97 | — | — | — | |
| DrawMotion2026.05 | 0.135 | 42.3 | 64.3 | 77.6 | 2.772 | 10.92 | — | 0.916 | 52.17 | |
| ReMoMask2026.02 | 0.138 | 45.3 | 68.2 | 80.5 | 2.682 | 10.83 | 2.017 | — | — | |
| LaMPcategory=VQ-VAE-based2026.01 | 0.141 | 47.9 | 69.1 | 82.6 | 2.704 | 10.93 | — | — | — | |
| LAMPText Encoder=LAMP2025.12 | 0.141 | 47.9 | 69.1 | 82.6 | 2.704 | 10.929 | — | — | — | |
| LAMPMethod Category=Mask-Modeling-based Motion Generator, w/ GRPO=false2025.12 | 0.141 | 0.479 | 0.691 | 82.6 | 2.704 | 10.929 | — | — | — | |
| LaMP2026.02 | 0.141 | 47.9 | 69.1 | 82.6 | 2.704 | 10.929 | — | — | — | |
| StickMotion2026.05 | 0.141 | 43 | 65.4 | 77.5 | 2.763 | 10.94 | — | 1.457 | 42.6 | |
| MoGenTScategory=VQ-VAE-based2026.01 | 0.143 | 44.5 | 67.1 | 79.7 | 2.711 | 10.92 | — | — | — | |
| MoGenSTMethod Category=Mask-Modeling-based Motion Generator, w/ GRPO=false2025.12 | 0.143 | 0.445 | 0.671 | 79.7 | 2.711 | 10.918 | — | — | — | |
| MoGenTS2026.02 | 0.143 | 44.5 | 67.1 | 79.7 | 2.711 | 10.918 | — | — | — | |
| MoTokPlanner=DDM, Downsampling=22026.03 | 0.144 | 42.7 | 64.2 | 76.2 | 2.856 | 10.92 | — | 1.325 | — | |
| ReMoDiffusecategory=Diffusion-based2026.01 | 0.155 | 42.7 | 64.1 | 76.5 | 2.814 | 10.8 | 1.239 | — | — | |
| ReMoDiffuseText Encoder=CLIP2025.12 | 0.155 | 42.7 | 64.1 | 76.5 | 2.814 | 10.8 | — | — | — | |
| ReMoDiffuseMethod Category=Diffusion-based Motion Generator, w/ GRPO=false2025.12 | 0.155 | 0.427 | 0.641 | 76.5 | 2.814 | 10.8 | — | — | — | |
| ReMoDiffuse2026.02 | 0.155 | 42.7 | 64.1 | 76.5 | 2.814 | 10.8 | 1.239 | — | — | |
| ReMoDiffuseFramework=Volume Diffusion, Ground truth motion length=True2024.06 | 0.155 | 42.7 | 64.1 | 76.5 | 2.814 | — | — | 1.239 | — | |
| ReMoDiffuseFramework=Volume Diffusion2024.06 | 0.155 | 42.7 | 64.1 | 76.5 | 2.814 | — | — | 1.239 | — | |
| ParTY2026.03 | 0.155 | 44.9 | 68 | 80.4 | 2.694 | 11.21 | — | 1.166 | — | |
| ReMoDiff2026.03 | 0.155 | 42.7 | 64.1 | 76.5 | 2.814 | 10.8 | — | 1.239 | — | |
| ReMoDiffuse2026.03 | 0.155 | 42.7 | 64.1 | 76.5 | 2.814 | 10.8 | — | 1.239 | — | |
| ReMoDiffuseStructure=Diffusion2026.04 | 0.155 | 42.7 | 64.1 | 76.5 | 2.814 | 10.8 | — | 1.239 | — | |
| ReMoDiffuse2026.05 | 0.155 | 42.7 | 64.1 | 76.5 | 2.814 | 10.8 | — | 1.239 | — | |
| ReMoDiffuse2026.05 | 0.155 | — | — | 76.5 | 2.814 | — | — | 1.239 | — | |
| Light-T2MFramework=Volume Diffusion, Ground truth motion length=True2024.06 | 0.161 | 44.4 | 67 | 79.4 | 2.746 | — | — | 1.005 | — | |
| Light-T2MFramework=Volume Diffusion2024.06 | 0.161 | 44.4 | 67 | 79.4 | 2.746 | — | — | 1.005 | — | |
| SegMoText Encoder=CLIP2025.12 | 0.163 | 44.3 | 66.3 | 78.4 | 2.733 | 10.797 | — | — | — | |
| RAMcategory=Diffusion-based2026.01 | 0.172 | 46.4 | 68.4 | 80.3 | 2.653 | 11.15 | 1.01 | — | — | |
| MoScaleStructure=Next-Scale AR, Steps (S)=182026.04 | 0.173 | 44.2 | 67.1 | 79.1 | 2.717 | 10.972 | — | 0.944 | — | |
| FineMoGencategory=Diffusion-based2026.01 | 0.178 | 43.2 | 64.9 | 77.2 | 2.869 | 10.85 | 1.877 | — | — | |
| FineMoGenEditable=Yes2025.12 | 0.178 | 43.2 | 64.9 | 77.2 | 2.869 | 10.85 | — | 1.877 | — | |
| LMRModel type=GPT-type2025.12 | 0.181 | 48.3 | 70.1 | 81.1 | 2.636 | 11.032 | — | — | — | |
| BAMMcategory=VQ-VAE-based2026.01 | 0.183 | 43.8 | 66.1 | 78.8 | 2.723 | 11.01 | 1.609 | — | — | |
| BAMMModel type=BERT-type2025.12 | 0.183 | 43.8 | 66.1 | 78.8 | 2.723 | 11.008 | — | — | — | |
| BAMMMethod Category=Mask-Modeling-based Motion Generator, w/ GRPO=false2025.12 | 0.183 | 0.438 | 0.661 | 78.8 | 2.723 | 11.008 | — | — | — | |
| BAMM2026.03 | 0.183 | 43.8 | 66.1 | 78.8 | 2.723 | 11.01 | — | 1.609 | — | |
| MoScaleStructure=Next-Scale AR, Steps (S)=42026.04 | 0.183 | 44.1 | 66.2 | 78.3 | 2.758 | 10.812 | — | 0.943 | — | |
| MoTokPlanner=DDM, Downsampling=42026.03 | 0.192 | 42.1 | 63.8 | 76 | 2.896 | 10.81 | — | 1.295 | — | |
| TCA-T2MYear=–2026.02 | 0.198 | 42.8 | 65.5 | 78 | 2.76 | 10.83 | — | 1.123 | — | |
| MoMaskcategory=VQ-VAE-based2026.01 | 0.204 | 43.3 | 65.6 | 78.1 | 2.779 | — | 1.131 | — | — | |
| MoMaskModel type=BERT-type2025.12 | 0.204 | 43.3 | 65.6 | 78.1 | 2.779 | — | — | — | — | |
| MoMaskText Encoder=CLIP2025.12 | 0.204 | 43.3 | 65.6 | 78.1 | 2.779 | — | — | — | — | |
| MoMaskMethod Category=Mask-Modeling-based Motion Generator, w/ GRPO=false2025.12 | 0.204 | 0.433 | 0.656 | 78.1 | 2.779 | — | — | — | — | |
| MoMask2026.02 | 0.204 | 43.3 | 65.6 | 78.1 | 2.779 | — | 1.131 | — | — | |
| MoRL2026.02 | 0.204 | 43.9 | 66.1 | 79.3 | 2.777 | 10.882 | 1.991 | — | — | |
| MoMaskFramework=VAE, Ground truth motion length=True2024.06 | 0.204 | 43.3 | 65.6 | 78.1 | 2.779 | — | — | 1.131 | — | |
| MoMaskFramework=VAE2024.06 | 0.204 | 43.3 | 65.6 | 78.1 | 2.779 | — | — | 1.131 | — | |
| MoMask2026.03 | 0.204 | 43.3 | 65.6 | 78.1 | 2.779 | — | — | 1.131 | — | |
| MoMask2026.03 | 0.204 | 43.3 | 65.6 | 78.1 | 2.779 | — | — | 1.131 | — | |
| MoMaskStructure=MaskedTrans2026.04 | 0.204 | 43.3 | 65.6 | 78.1 | 2.779 | — | — | 1.131 | — | |
| MoMask2026.05 | 0.204 | — | — | 78.1 | 2.779 | — | — | 1.131 | — | |
| MoTokPlanner=AR, Downsampling=22026.03 | 0.211 | 42.3 | 63.3 | 75 | 3.048 | 11.31 | — | 1.154 | — | |
| BADcategory=VQ-VAE-based2026.01 | 0.221 | 41.7 | 63.1 | 75 | 2.941 | 11 | 1.17 | — | — | |
| Momask*Year=20242026.02 | 0.228 | 41.5 | 63.5 | 76.2 | 2.889 | 10.612 | — | 1.208 | — | |
| SiT2026.02 | 0.242 | 38.7 | 61 | 74.9 | — | — | — | — | — | |
| CoMoOperation mode=Reconstruction, Editable=Yes2025.12 | 0.254 | 38.7 | 60.3 | 73 | 3.046 | 10.73 | — | — | — | |
| LaMoGenComposer=Human2026.03 | 0.254 | 42.4 | 65.7 | 78.2 | 2.821 | 11.09 | — | 0.979 | — | |
| StableMoFusioncategory=Diffusion-based2026.01 | 0.258 | 44.5 | 66 | 78.2 | — | 10.94 | 1.362 | — | — | |
| MDMenhancement=EasyTune2026.02 | 0.284 | 44.2 | 65.5 | 77.3 | 2.755 | 11.27 | — | — | — | |
| Motion-R1Method Category=Motion-aware LLM, w/ GRPO=true, support both text and motion outputs=true2025.12 | 0.287 | 0.431 | 0.638 | 76.1 | 3.196 | 10.875 | — | — | — | |
| Saladcategory=Diffusion-based2026.01 | 0.296 | 47.7 | 71.1 | 82.8 | 2.585 | 11.1 | 1.004 | — | — | |
| MoTokPlanner=AR, Downsampling=42026.03 | 0.297 | 41.8 | 61.9 | 73.4 | 3.075 | 11.15 | — | 1.102 | — | |
| Light-RDM-1Framework=Volume Diffusion, Ground truth motion length=True2024.06 | 0.299 | 44.3 | 66.5 | 79.1 | 2.772 | — | — | 1.05 | — | |
| Light-RDM-1Framework=Volume Diffusion2024.06 | 0.299 | 44.3 | 66.5 | 79.1 | 2.772 | — | — | 1.05 | — | |
| MotionMamba2026.02 | 0.307 | 41.9 | 64.5 | 76.5 | 3.021 | 11.02 | — | — | — | |
| Mo.MambaYear=20242026.02 | 0.307 | 41.9 | 64.5 | 76.5 | 3.021 | 11.02 | — | 1.678 | — | |
| MotionMambaFramework=Volume Diffusion, Ground truth motion length=True2024.06 | 0.307 | 41.9 | 64.5 | 76.5 | 3.021 | — | — | 1.678 | — | |
| MotionMambaFramework=Volume Diffusion2024.06 | 0.307 | 41.9 | 64.5 | 76.5 | 3.021 | — | — | 1.678 | — | |
| MogoModel type=GPT-type2025.12 | 0.313 | 42 | 63.4 | 75.4 | 2.957 | — | — | — | — | |
| GraphMotionEditable=No2025.12 | 0.313 | 42.9 | 64.8 | 76.9 | 3.076 | 11.12 | — | 3.627 | — | |
| MMMcategory=VQ-VAE-based2026.01 | 0.316 | 40.4 | 62.1 | 74.4 | 2.977 | 10.91 | 1.232 | — | — | |
| MMMText Encoder=CLIP2025.12 | 0.316 | 40.4 | 62.1 | 74.4 | 2.977 | 10.91 | — | — | — | |
| MMMMethod Category=Mask-Modeling-based Motion Generator, w/ GRPO=false2025.12 | 0.316 | 0.404 | 0.621 | 74.4 | 2.977 | 10.91 | — | — | — | |
| MMMYear=20242026.02 | 0.316 | 40.4 | 62.1 | 74.4 | 2.977 | 10.91 | — | 1.232 | — | |
| MMM2026.03 | 0.316 | 40.4 | 62.1 | 74.4 | 2.977 | 10.91 | — | 1.232 | — | |
| MMMStructure=MaskedTrans2026.04 | 0.316 | 40.4 | 62.1 | 74.4 | 2.977 | 10.91 | — | 1.232 | — | |
| PGR²MEditable=Yes, Use of fine-grained keywords=No, Transformer configuration=Base and Refine Transformers2025.12 | 0.328 | 42.4 | 63.9 | 75.7 | 2.875 | 10.99 | — | 1.376 | — | |
| CoMo2026.02 | 0.332 | 42.2 | 63.8 | 76.5 | 2.873 | 10.95 | — | — | — | |
| CoMoEditable=Yes, Use of fine-grained keywords=Yes2025.12 | 0.332 | 42.2 | 63.8 | 76.5 | 2.873 | 10.95 | — | 1.249 | — | |
| CoMoText Encoder=CLIP2025.12 | 0.332 | 42.2 | 63.8 | 76.5 | 2.873 | 10.95 | — | — | — | |
| CoMoYear=20242026.02 | 0.332 | 42.2 | 63.8 | 76.5 | 2.873 | 10.95 | — | 1.249 | — | |
| CoMo2026.03 | 0.332 | 42.2 | 63.8 | 76.5 | 2.873 | 10.95 | — | 1.249 | — | |
| Ours (S2, w/ IRMoGen)Method Category=Motion-aware LLM, w/ GRPO=false, support both text and motion outputs=true2025.12 | 0.389 | 0.419 | 0.642 | 76.3 | 2.908 | 11.096 | — | — | — | |
| CoMoEditable=Yes, Use of fine-grained keywords=No2025.12 | 0.399 | 39.9 | — | — | 2.898 | 11.26 | — | — | — | |
| MLDcategory=Diffusion-based2026.01 | 0.404 | 39 | 60.9 | 73.4 | 3.204 | 10.8 | 2.192 | — | — | |
| MLDModel type=diffusion-type2025.12 | 0.404 | 39 | 60.9 | 73.4 | 3.204 | 10.8 | — | — | — | |
| MLDEditable=No2025.12 | 0.404 | 39 | 60.9 | 73.4 | 3.204 | 10.8 | — | 2.192 | — | |
| MLDText Encoder=CLIP2025.12 | 0.404 | 39 | 60.9 | 73.4 | 3.204 | 10.8 | — | — | — |