Research map / Video / Video generation
FreeMotion: MoCap-Free Human Motion Synthesis with Multimodal Large Language Models
Zhikai Zhang, Yitang Li, Haofeng Huang, Mingxian Lin, Li Yi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use GPT-4V keyframes plus physics tracking instead of data-driven MDM/MLD | FreeMotion · HumanAct12 | user preference average: 30.83% -> 46.50% | Improved |
| FreeMotion vs data-driven baselines on individual HumanAct12 actions | FreeMotion · HumanAct12 | user preference: Sit 26.00% vs MLD 44.00%; Walk 68.00% vs 22.00% | Mixed |
| MLLM keyframes vs CLIP-based zero-shot methods on style transfer | FreeMotion · Style transfer | user preference average: 22.25% -> 58.67% | Improved |
| MLLM keyframes vs MotionCLIP/AvatarCLIP on Olympic sports | FreeMotion · Olympic sports | user preference | Improved |
| add detailed body-part descriptions in keyframe designer (ablation) | FreeMotion · HumanAct12 | user preference: 26.00% -> 74.00% | Improved |
| add visual feedback loop in keyframe animator (ablation) | FreeMotion · HumanAct12 | user preference: 32.00% -> 68.00% | Improved |
| MLLM-driven lying down on beds with rich contact | FreeMotion · Human-scene interaction: Lie Down | success rate (%): 81.5 (UniHSI) -> 60 | Hurt |
| FreeMotion vs ALLSTEPS on stepping stones | FreeMotion · Stepping stones | max step distance | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MotionCLIP — MotionCLIP: Exposing Human Motion Generation to CLIP Space (ECCV 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Enhanced Fine-Grained Motion Diffusion for Text-Driven Human Motion Synthesis (AAAI 2024 · similarity 0.89)
- MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators (AAAI 2024 · similarity 0.88)
- The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion (CVPR 2025 · similarity 0.88)
- HMVLM:Human Motion-Vision-Language Model via MoE LoRA (NeurIPS 2025 · similarity 0.88)
- Seamless Human Motion Composition with Blended Positional Encodings (CVPR 2024 · similarity 0.88)
- Move as You Say Interact as You Can: Language-guided Human Motion Generation with Scene Affordance (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
