Research map / 3D vision / Human pose estimation
A Unified Framework for Multi-View Multi-Class Object Pose Estimation
Chi Li, Jin Bai, Gregory D. Hager
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 multi-view voting (MV5) to MCN | MCN · YCB-Video (all objects) (RGB) | mPCK: 75.1 -> 80.2 | Improved |
| add multi-view voting (MV5) to MCN | MCN · YCB-Video (all objects) (RGB-D) | mPCK: 90.6 -> 94.3 | Improved |
| add multi-view voting (MV5) to MCN | MCN · JHUScene-50 (all) (RGB-D) | mPCK: 78.9 -> 84.8 | Improved |
| add ICP refinement to MCN | MCN · YCB-Video (all objects) (RGB-D) | mPCK: 90.6 -> 93.3 | Improved |
| add bin and delta representation (vs plain regression) (ablation) | MCN · YCB-Video (RGB, ablation) | mPCK: 61.0 -> 66.2 | Improved |
| add bin and delta representation (vs plain regression) (ablation) | MCN · YCB-Video (RGB-D, ablation) | mPCK: 61.8 -> 89.5 | Improved |
| add tiled class map to BD + Seg (ablation) | MCN · YCB-Video (RGB, ablation) | mPCK: 66.2 -> 80.2 | Improved |
| add deep supervision of segmentation to BD + TC (ablation) | MCN · YCB-Video (RGB, ablation) | mPCK: 68.5 -> 80.2 | Improved |
| add deep supervision of segmentation to BD + TC (ablation) | MCN · JHUScene-50 (RGB-D, ablation) | mPCK: 76.4 -> 78.9 | Improved |
| use tiled class map instead of separate output branch per class (ablation) | MCN · YCB-Video (RGB, ablation) | mPCK: 73.8 -> 80.2 | Improved |
| share one network across classes instead of separate network per class (ablation) | MCN · YCB-Video (RGB, ablation) | mPCK: 62.1 -> 80.2 | Improved |
| share one network across classes instead of separate network per class (ablation) | MCN · JHUScene-50 (RGB-D, ablation) | mPCK: 66.9 -> 78.9 | Improved |
Closest papers by meaning
- A Comparative Analysis and Study of Multiview CNN Models for Joint Object Categorization and Pose Estimation (ICML 2016 · similarity 0.91)
- RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews From Unsupervised Viewpoints (CVPR 2018 · similarity 0.90)
- Multi-Path Learning for Object Pose Estimation Across Domains (CVPR 2020 · similarity 0.90)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.88)
- NOPE: Novel Object Pose Estimation from a Single Image (CVPR 2024 · similarity 0.88)
- FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects (CVPR 2024 · 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.
