Research map / Video / Video generation
FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis
Ke Fan, Junshu Tang, Weijian Cao, Ran Yi, Moran Li, Jingyu Gong, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Lizhuang Ma
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 |
|---|---|---|---|
| decouple generation and interaction modules instead of randomly masking cross-attention in InterGen | multi-person motion synthesis · InterHuman two-person | FID: 13.404 -> 6.740 | Improved |
| same decoupled framework for single-person motion | FreeMotion vs InterGen* · InterHuman re-annotated single-person text | FID: 23.415 -> 12.975 | Improved |
| add interaction module and InterDes interactive descriptions to the generation module (ablation) | FreeMotion · InterHuman two-person | FID: 10.749 (GM) -> 6.740 | Improved |
| add interaction module without InterDes text (ablation) | generation module only (GM*) · InterHuman two-person | FID: 8.842 -> 8.792 | No clear effect |
| add interactive descriptions when only the generation module is finetuned (ablation) | GM · InterHuman two-person | FID: 8.842 -> 10.749 | Hurt |
| use FreeMotion instead of MDM for diversity within same text | MModality · InterHuman test | MModality: 2.355 (MDM) vs 1.226 | Hurt |
Later papers that compared with this method
3 later accepted papers report FreeMotion as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Unified Number-Free Text-to-Motion Generation Via Flow Matching (CVPR 2026 · better on 6 of 6 shared results)
- InterSyn: Interleaved Learning for Dynamic Motion Synthesis in the Wild (ICCV 2025 · better on 9 of 11 shared results)
- PINO: Person-Interaction Noise Optimization for Long-Duration and Customizable Motion Generation of Arbitrary-Sized Groups (ICCV 2025 · better on 2 of 2 shared results)
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.
- InterGen* — InterGen: Diffusion-Based Multi-human Motion Generation Under Complex Interactions (IJCV 2024) · better on 6 of 7 shared results
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
- FreeMotion: MoCap-Free Human Motion Synthesis with Multimodal Large Language Models (ECCV 2024 · similarity 0.88)
- Enhanced Fine-Grained Motion Diffusion for Text-Driven Human Motion Synthesis (AAAI 2024 · similarity 0.85)
- Seamless Human Motion Composition with Blended Positional Encodings (CVPR 2024 · similarity 0.85)
- MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators (AAAI 2024 · similarity 0.85)
- InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint (NeurIPS 2024 · similarity 0.85)
- ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration (NeurIPS 2026 · similarity 0.85)
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.
