Research map / 3D vision / Human pose estimation
Holistic++ Scene Understanding: Single-View 3D Holistic Scene Parsing and Human Pose Estimation With Human-Object Interaction and Physical Commonsense
Yixin Chen, Siyuan Huang, Tao Yuan, Siyuan Qi, Yixin Zhu, Song-Chun Zhu
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 physical commonsense prior (ablation) | Holistic++ · PiGraphs | 3D object IoU (%): 23.5% to 24.9% | Improved |
| add physical commonsense prior (ablation) | Holistic++ · PiGraphs | physical violation (m): 0.223m to 0.150m | Improved |
| add HOI prior and top-down sampling (sit) (ablation) | Holistic++ · PiGraphs/Synthetic SUN RGB-D, sit | 3D object IoU (%): 26.9 -> 27.8 | Improved |
| add HOI prior and top-down sampling (sit) (ablation) | Holistic++ · PiGraphs/Synthetic SUN RGB-D, sit | 3D pose error (m): 0.590 -> 0.521 | Improved |
| add HOI prior and top-down sampling (sit) (ablation) | Holistic++ · PiGraphs/Synthetic SUN RGB-D, sit | miss-detection rate (%): 15.2 -> 13.1 | Improved |
| add HOI prior and top-down sampling (hold) (ablation) | Holistic++ · PiGraphs/Synthetic SUN RGB-D, hold | 3D object IoU (%): 17.4 -> 17.6 | Improved |
| add HOI prior and top-down sampling (hold) (ablation) | Holistic++ · PiGraphs/Synthetic SUN RGB-D, hold | 3D pose error (m): 0.517 -> 0.490 | Improved |
| add HOI prior and top-down sampling (hold) (ablation) | Holistic++ · PiGraphs/Synthetic SUN RGB-D, hold | miss-detection rate (%): 78.9 -> 54.6 | Improved |
| add HOI prior and top-down sampling (use laptop) (ablation) | Holistic++ · PiGraphs/Synthetic SUN RGB-D, use laptop | 3D object IoU (%): 14.1 -> 15.0 | Improved |
| add HOI prior and top-down sampling (use laptop) (ablation) | Holistic++ · PiGraphs/Synthetic SUN RGB-D, use laptop | 3D pose error (m): 0.544 -> 0.534 | Improved |
| add HOI prior and top-down sampling (use laptop) (ablation) | Holistic++ · PiGraphs/Synthetic SUN RGB-D, use laptop | miss-detection rate (%): 58.8 -> 43.3 | Improved |
| add HOI prior and top-down sampling (read) (ablation) | Holistic++ · PiGraphs/Synthetic SUN RGB-D, read | 3D object IoU (%): 14.5 -> 14.3 | Hurt |
Closest papers by meaning
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.87)
- SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (CVPR 2024 · similarity 0.87)
- Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions (CVPR 2025 · similarity 0.87)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.86)
- ChatPose: Chatting about 3D Human Pose (CVPR 2024 · similarity 0.86)
- Reconstructing People, Places, and Cameras (CVPR 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.
