| Motion Anything: Any to Motion Generation | ✓ Link | 0.131 | 0.802 | 10.94 | 1.374 | Motion Anything | 2025-03-10 |
| Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss | ✓ Link | 0.155 | 0.789 | 10.902 | | Free-T2M (StableMoFusion) | 2025-01-30 |
| ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model | ✓ Link | 0.155 | 0.765 | 10.80 | 1.239 | ReMoDiffuse | 2023-04-03 |
| BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis | | 0.164 | 0.803 | 10.833 | 1.098 | BiPO | 2024-11-28 |
| DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding | | 0.169 | 0.775 | | 1.266 | DisCoRD (+MoMask) | 2024-11-29 |
| FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing | ✓ Link | 0.178 | 0.772 | 10.85 | 1.877 | FineMoGen | 2023-12-22 |
| BAMM: Bidirectional Autoregressive Motion Model | ✓ Link | 0.183 | 0.788 | 11.008 | 1.609 | BAMM | 2024-03-28 |
| MoMask: Generative Masked Modeling of 3D Human Motions | ✓ Link | 0.204 | 0.781 | | 1.131 | MoMask | 2023-11-29 |
| BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation | ✓ Link | 0.221 | 0.750 | 11.000 | 1.170 | BAD (OAAS) | 2024-09-17 |
| EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation | ✓ Link | 0.261 | 0.780 | 10.96 | 1.343 | EMDM | 2023-12-04 |
| MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model | | 0.294 | 0.787 | 10.827 | 1.254 | MotionPCM | 2025-01-31 |
| Motion Mamba: Efficient and Long Sequence Motion Generation | ✓ Link | 0.307 | 0.765 | 11.02 | 1.678 | Motion Mamba | 2024-03-12 |
| Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs | ✓ Link | 0.313 | 0.769 | 11.12 | 3.627 | GraphMotion | 2023-09-21 |
| MMM: Generative Masked Motion Model | ✓ Link | 0.316 | 0.744 | 10.910 | 1.232 | MMM (gt length) | 2023-12-06 |
| GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation | ✓ Link | 0.371 | 0.751 | 10.933 | 2.732 | GUESS | 2024-01-04 |
| Executing your Commands via Motion Diffusion in Latent Space | ✓ Link | 0.404 | 0.734 | 10.80 | 2.192 | MLD | 2022-12-08 |
| MMM: Generative Masked Motion Model | ✓ Link | 0.429 | 0.718 | 10.633 | 1.105 | MMM (predict length) | 2023-12-06 |
| ParCo: Part-Coordinating Text-to-Motion Synthesis | ✓ Link | 0.453 | 0.772 | 10.95 | 1.245 | ParCo | 2024-03-27 |
| DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion | | 0.468 | 0.760 | 10.873 | 2.062 | DiverseMotion | 2023-09-04 |
| Human Motion Diffusion Model | ✓ Link | 0.497 | 0.396 | 10.847 | 1.907 | MDM | 2022-09-29 |
| T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations | ✓ Link | 0.514 | 0.745 | 10.921 | 1.570 | T2M-GPT (τ ∈ U[0, 1]) | 2023-01-15 |
| Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model | | 0.571 | 0.745 | 10.93 | 1.019 | Fg-T2M | 2023-09-12 |
| T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations | ✓ Link | 0.717 | 0.737 | 10.862 | 1.912 | T2M-GPT (τ = 0.5) | 2023-01-15 |
| T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations | ✓ Link | 0.737 | 0.716 | 11.198 | 2.309 | T2M-GPT (τ = 0) | 2023-01-15 |
| AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism | ✓ Link | 0.870 | 0.751 | 10.96 | 2.281 | AttT2M | 2023-09-02 |
| MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model | ✓ Link | 1.954 | 0.739 | 11.10 | 0.730 | MotionDiffuse | 2022-08-31 |
| Generating Diverse and Natural 3D Human Motions From Text | ✓ Link | 3.022 | 0.681 | 10.72 | 2.052 | T2M | 2022-01-01 |
| TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts | ✓ Link | 3.599 | 0.587 | 9.473 | 3.292 | TM2T | 2022-07-04 |
| Executing your Commands via Motion Diffusion in Latent Space | ✓ Link | 3.717 | 0.687 | 10.84 | 0.532 | TEMOS | 2022-12-08 |
| TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts | ✓ Link | 6.545 | 0.483 | 9.073 | | Language2Pose | 2022-07-04 |
| TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts | ✓ Link | 12.12 | 0.338 | 9.334 | | Text2Gesture | 2022-07-04 |