Research map / Video / Video generation
A Unified Framework for Motion Reasoning and Generation in Human Interaction
Jeongeun Park, Sungjoon Choi, Sangdoo Yun
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 |
|---|---|---|---|
| add the Inter-MT2 dataset to training (ablation) | VIM · Motion reasoning | Coherence: 2.770 -> 5.252 | Improved |
| add the Inter-MT2 dataset to training (ablation) | VIM · Motion reasoning | MAUVE: 0.004 -> 0.794 | Improved |
| add the Inter-MT2 dataset to training (ablation) | VIM · Motion editing | FID: 0.080 -> 0.064 | Improved |
| add the Inter-MT2 dataset to training (ablation) | VIM · Motion editing | MPJPE: 0.908 -> 0.758 | Improved |
| add the Inter-MT2 dataset to training (ablation) | VIM · Reaction generation | MPJPE: 0.984 -> 0.691 | Improved |
| add the Inter-MT2 dataset to training (ablation) | VIM · Reaction generation | FID: 0.031 -> 0.019 | Improved |
| add the Inter-MT2 dataset to training (ablation) | VIM · Text-to-motion | FID: 0.082 -> 0.059 | Improved |
| add the Inter-MT2 dataset to training (ablation) | VIM · Text-to-motion | R Top3: 0.561 -> 0.568 | Improved |
| add the Inter-MT2 dataset to training (ablation) | VIM · Motion-to-text | R Top3: 0.894 -> 0.901 | Improved |
| use unified model instead of two-stage TM2T + GPT-4o | VIM · Motion reasoning | Coherence: 4.266 -> 5.252 | Improved |
| use unified VIM instead of two-stage TM2T + InterGEN | VIM · Motion editing | FID: 0.110 -> 0.064 | Improved |
| use RQ-VAE tokenizer instead of VQ-VAE (ablation) | VIM · Reaction generation | MPJPE: 1.109 -> 0.691 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- InterGEN — InterGen: Diffusion-Based Multi-human Motion Generation Under Complex Interactions (IJCV 2024) · better on 1 of 2 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
- Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs (ICLR 2025 · similarity 0.92)
- The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion (CVPR 2025 · similarity 0.91)
- CigTime: Corrective Instruction Generation Through Inverse Motion Editing (NeurIPS 2024 · similarity 0.90)
- InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction (NeurIPS 2024 · similarity 0.90)
- MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities (CVPR 2025 · similarity 0.90)
- HSI-GPT: A General-Purpose Large Scene-Motion-Language Model for Human Scene Interaction (CVPR 2025 · similarity 0.89)
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.
