Research map / 3D vision / 3D generation
Human-Aware Object Placement for Visual Environment Reconstruction
Hongwei Yi, Chun-Hao P. Huang, Dimitrios Tzionas, Muhammed Kocabas, Mohamed Hassan, Siyu Tang, Justus Thies, Michael J. Black
Check 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 accumulated human-scene interaction constraints to refine scene layout | MOVER · PROX qualitative, 2D GT | 3D IoU: 0.267 -> 0.383 | Improved |
| Use accumulated human-scene interaction constraints to refine scene layout | MOVER · PiGraphs | 3D IoU: 26.3 -> 27.8 | Improved |
| Use accumulated human-scene interaction constraints to refine scene layout | MOVER · PROX quantitative | 3D IoU: 0.239 -> 0.390 | Improved |
| Use accumulated human-scene interaction constraints to refine scene layout | MOVER · PROX qualitative, 2D GT | Contactness: 0.491 -> 0.673 | Improved |
| Use accumulated human-scene interaction constraints to refine scene layout | MOVER · PROX qualitative, 2D GT | Non-Col: 0.988 -> 0.986 | Hurt |
| Add camera-orientation and ground-plane constraints using foot contact (ablation) | MOVER HPS refinement · PROX quantitative HPS | PJE: 219.62 -> 176.41 | Improved |
| Add body-scene SDF loss after +CamGP (ablation) | MOVER HPS refinement · PROX quantitative HPS | PJE: 176.41 -> 175.98 | Improved |
| Add contact loss after +CamGP+SDF (ablation) | MOVER HPS refinement · PROX quantitative HPS | PJE: 175.98 -> 174.37 | Improved |
| Add contact constraint without depth-order or collision constraints (ablation) | MOVER scene reconstruction · PROX qualitative, 2D GT | Contactness: 0.673 -> 0.773 | Improved |
| Use depth-order constraint without the other HSI constraints (ablation) | MOVER scene reconstruction · PROX qualitative, 2D GT | 3D IoU | Improved |
| Use depth-order constraint without the other HSI constraints (ablation) | MOVER scene reconstruction · PROX qualitative, 2D GT | Contactness | Hurt |
| Use all HSI constraints together rather than depth-order constraint alone (ablation) | MOVER scene reconstruction · PROX qualitative, 2D GT | Contactness | Improved |
Closest papers by meaning
- HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos (ECCV 2024 · similarity 0.91)
- Reconstructing People, Places, and Cameras (CVPR 2025 · similarity 0.90)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.89)
- UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.88)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.87)
- InteractVLM: 3D Interaction Reasoning from 2D Foundational Models (CVPR 2025 · similarity 0.87)
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.
