Research map / 3D vision / 3D generation
Human Motion Synthesis in 3D Scenes via Unified Scene Semantic Occupancy
Jingyu Gong, Kunkun Tong, Zhuoran Chen, Chuanhan Yuan, Mingang Chen, Zhizhong Zhang, Xin Tan, Yuan Xie
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 SSOMotion instead of DIMOS | locomotion · Locomotion (ShapeNet cluttered scenes) | avg. distance to target (m): 0.04 -> 0.02 | Improved |
| use SSOMotion instead of DIMOS | locomotion · Locomotion (ShapeNet cluttered scenes) | foot contact score: 0.99 -> 0.90 | Hurt |
| use SSOMotion instead of DIMOS | locomotion · Locomotion (ShapeNet cluttered scenes) | task time (s): 6.43 -> 3.60 | Improved |
| use SSOMotion instead of DIMOS | sitting interaction · Human-scene interaction, sit | max penetration: 10.61 -> 6.78 | Improved |
| use SSOMotion instead of DIMOS | lying interaction · Human-scene interaction, lie | mean penetration: 9.90 -> 5.74 | Improved |
| use SSOMotion instead of DIMOS | lying interaction · Human-scene interaction, lie | task time (s): 4.20 -> 3.69 | Improved |
| add bi-directional tri-plane decomposition (ablation) | SSO scene comprehension · Scene comprehension cost | compute cost (GFLOPs): 20783.78 -> 421.73 | Improved |
| add dimensionality reduction of CLIP semantic features (ablation) | SSO scene comprehension · Scene comprehension cost | compute cost (GFLOPs): 20783.78 -> 21.21 | Improved |
| add both decomposition and dimensionality reduction (ablation) | SSO scene comprehension · Scene comprehension cost | compute cost (GFLOPs): 20783.78 -> 0.49 | Improved |
Closest papers by meaning
- SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent (NeurIPS 2025 · similarity 0.87)
- InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior (ICLR 2024 · similarity 0.87)
- Move as You Say Interact as You Can: Language-guided Human Motion Generation with Scene Affordance (CVPR 2024 · similarity 0.86)
- SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (CVPR 2024 · similarity 0.86)
- Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance (NeurIPS 2025 · similarity 0.86)
- Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model (AAAI 2025 · similarity 0.86)
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.
