AI Paper Atlas

Research map / 3D vision / 3D generation

MMG-VL: A Vision-Language Driven Approach for Multi-Person Motion Generation

Songyuan Yang, Wanrong Huang, Yinuo Liu, Zhang Ke-Di, Xihuai He, Shaowu Yang, Huibin Tan

AAAI 2026 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Spatial-Semantic Grounding Loss (LSSG) to the planner (ablation)MMG-VL · HumanVL (4-person ablation)Environmental Alignment: 6.95 -> 7.80Improved
add LSSG to the planner (ablation)MMG-VL · HumanVL (4-person ablation)Multi-person Coordination: 8.75 -> 8.89No clear effect
add Lenv (SDF penetration loss) to the synthesizer (ablation)MMG-VL · HumanVL (4-person ablation)Penetration mean: 0.873 -> 0.251Improved
add Lenv to the synthesizer (ablation)MMG-VL · HumanVL (4-person ablation)Environmental Alignment: 5.82 -> 7.80Improved
add Lenv to the synthesizer (ablation)MMG-VL · HumanVL (4-person ablation)Diversity: 1.321 -> 1.310Hurt
add Lcoord (coordination loss) to the synthesizer (ablation)MMG-VL · HumanVL (4-person ablation)Multi-person Coordination: 6.23 -> 8.89Improved
add Lcoord to the synthesizer (ablation)MMG-VL · HumanVL (4-person ablation)Penetration mean: 0.288 -> 0.251Improved
add both Lenv and Lcoord (ablation)MMG-VL · HumanVL (4-person ablation)Environmental Alignment: 5.11 -> 7.80Improved
add both Lenv and Lcoord (ablation)MMG-VL · HumanVL (4-person ablation)Multi-person Coordination: 5.95 -> 8.89Improved
add both Lenv and Lcoord (ablation)MMG-VL · HumanVL (4-person ablation)Diversity: 1.328 -> 1.310Hurt
use MMG-VL CMS instead of MotionDiffusetext-to-motion synthesis · HumanML3DFID: 0.630 -> 0.501Improved
use MMG-VL instead of best HSI baseline with ground-truth 3D scenessingle-person scene-aware generation · HumanVL (single-person, vs HSI)Penetration mean: 0.387 -> 0.283Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy