Research map / 3D vision / 3D generation
HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perception
Wei Yao, Yunlian Sun, Hongwen Zhang, Yebin Liu, Jinhui Tang
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 |
|---|---|---|---|
| HOSIG over LINGO | LINGO · TRUMANS object locomotion | success rate: 0.2333 -> 0.9333 | Improved |
| HOSIG over CHOIS | CHOIS · TRUMANS object locomotion | success rate: 0.0333 -> 0.9333 | Improved |
| HOSIG over LINGO | LINGO · TRUMANS scene interaction | penetration rate: 0.3175 -> 0.1851 | Improved |
| HOSIG over LINGO | LINGO · TRUMANS scene interaction | mean penetration: 0.3745 -> 0.6562 | Hurt |
| HOSIG over LINGO | LINGO · TRUMANS scene interaction | max penetration: 89.5247 -> 201.8264 | Hurt |
| HOSIG over LINGO | LINGO · TRUMANS object locomotion | task time: 11.5033 (CHOIS) / 16.6100 (LINGO) vs 13.0367 | Hurt |
| HOSIG over baselines | LINGO/CHOIS · TRUMANS object interaction | contact rate: 0.2418 -> 0.9800 | Improved |
| HOSIG over baselines on hand-object penetration | LINGO · TRUMANS object interaction | mean penetration: 0.0001 -> 0.0007 | Hurt |
| add scene distance loss to SGAP (ablation) | SGAP · TRUMANS scene interaction | penetration rate: 0.7037 -> 0.5533 | Improved |
| add scene distance loss to SGAP (ablation) | SGAP · TRUMANS scene interaction | mean penetration: 3.4615 -> 0.4484 | Improved |
| add scene perception (B_s and loss) to SGAP (ablation) | SGAP · TRUMANS scene interaction | penetration rate: 0.6611 -> 0.5533 | Improved |
| add scene perception to SGAP (ablation) | SGAP · TRUMANS object interaction | contact rate: 1.0000 -> 0.9833 | No clear effect |
Closest papers by meaning
- CG-HOI: Contact-Guided 3D Human-Object Interaction Generation (CVPR 2024 · similarity 0.90)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.89)
- DiffGrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model (AAAI 2025 · similarity 0.89)
- Guiding Human-Object Interactions with Rich Geometry and Relations (CVPR 2025 · similarity 0.88)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.88)
- SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios (NeurIPS 2025 · similarity 0.88)
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.
