Research map / 3D vision / Human pose estimation
Holistic Pose Graph: Modeling Geometric Structure Among Objects in a Scene Using Graph Inference for 3D Object Prediction
Jiwei Xiao, Ruiping Wang, Xilin Chen
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 Holistic Pose Graph inference (ablation) | Ours · SUN RGB-D 3D object detection | mAP: 27.39 -> 32.75 | Improved |
| add consistency loss (ablation) | Ours · SUN RGB-D 3D object detection | mAP: 27.99 -> 32.75 | Improved |
| add HPG graph inference (ablation) | Ours · SUN RGB-D HPE | PhrAccI: 12.17 -> 16.43 | Improved |
| add HPG graph inference (ablation) | Ours · SUN RGB-D HPE | RelAcc: 33.79 -> 40.48 | Improved |
| add HPG (ablation) | Ours · SUN RGB-D 3D box estimation | Acc: 49.23 -> 54.27 | Improved |
| add consistency loss (ablation) | Ours · SUN RGB-D HPE | PhrAccI: 16.43 -> 18.49 | Improved |
| add consistency loss (ablation) | Ours · SUN RGB-D HPE | RelAcc: 40.48 -> 40.09 | No clear effect |
| add consistency loss (ablation) | Ours · SUN RGB-D 3D box estimation | Acc: 49.58 -> 54.27 | Improved |
| increase message passing iterations beyond 3 (ablation) | Ours · SUN RGB-D | all metrics | No clear effect |
| sample more graph edges (ablation) | Ours · SUN RGB-D | all metrics | Improved |
| use HPG-based method instead of Total3D baseline | Ours vs Total3D · SUN RGB-D 3D object detection | mAP: 26.38 -> 32.75 | Improved |
| use HPG-based method instead of Total3D baseline | Ours vs Total3D · SUN RGB-D HPE | PhrAccI: 12.88 -> 18.49 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PerspectiveNet — PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments (NeurIPS 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships (CVPR 2024 · similarity 0.87)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.87)
- Learning to Filter Outlier Edges in Global SfM (CVPR 2025 · similarity 0.87)
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · similarity 0.86)
- Deep Semantic Graph Transformer for Multi-View 3D Human Pose Estimation (AAAI 2024 · similarity 0.86)
- NOPE: Novel Object Pose Estimation from a Single Image (CVPR 2024 · 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.
