Research map / 3D vision / Human pose estimation
PR-GCN: A Deep Graph Convolutional Network With Point Refinement for 6D Pose Estimation
Guangyuan Zhou, Huiqun Wang, Jiaxin Chen, Di Huang
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 PRN point refinement (ablation) | DGCNN baseline · Linemod | ADD(-S) (%): 94.8 -> 96.8 | Improved |
| add MMF-GCN fusion (ablation) | DGCNN baseline · Linemod | ADD(-S) (%): 94.8 -> 96.9 | Improved |
| add both PRN and MMF-GCN (ablation) | DGCNN baseline · Linemod | ADD(-S) (%): 94.8 -> 98.9 | Improved |
| add PRN (ablation) | DenseFusion · YCB-Video | ADD-S (%): 93.1 -> 94.1 | Improved |
| add MMF-GCN (ablation) | DenseFusion · YCB-Video | ADD-S (%): 93.1 -> 93.5 | Improved |
| add PRN and MMF-GCN (ablation) | DenseFusion · YCB-Video | ADD-S (%): 93.1 -> 94.9; 96.8 -> 98.1 (<2cm) | Improved |
| add MMF-GCN (ablation) | PVN3D · YCB-Video | ADD-S (%): 95.5 -> 96.2; 97.6 -> 98.4 (<2cm) | Improved |
| use ground-truth segmentation instead of PoseCNN segmentation (ablation) | PR-GCN · YCB-Video | ADD-S AUC (%): 95.0 -> 96.9 (AUC) | Improved |
| use PVN3D segmentation instead of PoseCNN segmentation (ablation) | PR-GCN · YCB-Video | ADD-S AUC (%): 95.0 -> 95.8 (AUC) | Improved |
| add single-resolution PRN loss (PRN vs none) (ablation) | PR-GCN · YCB-Video | ADD-S (%): 94.0 -> 94.6 | Improved |
| use multi-resolution instead of single-resolution PRN loss (ablation) | PR-GCN · YCB-Video | ADD-S (%): 94.6 -> 95.8 | Improved |
| single-resolution loss on <2cm metric (ablation) | PR-GCN · YCB-Video | ADD-S <2cm (%): 97.1 -> 96.6 | Hurt |
Later papers that compared with this method
1 later accepted paper reports PR-GCN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation (ECCV 2022 · better on 4 of 4 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.
- PVN3D — PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation (CVPR 2020) · better on 4 of 4 shared results
- DenseFusion — DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion (CVPR 2019) · better on 3 of 3 shared results
- PVNet — PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation (CVPR 2019) · better on 2 of 2 shared results
- DPOD — DPOD: 6D Pose Object Detector and Refiner (ICCV 2019) · better on 1 of 1 shared result
- Pix2Pose — Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation (ICCV 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
- GDRNPP: A Geometry-Guided and Fully Learning-Based Object Pose Estimator (TPAMI 2025 · similarity 0.89)
- GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation (CVPR 2021 · similarity 0.89)
- Deep Model-Based 6D Pose Refinement in RGB (ECCV 2018 · similarity 0.88)
- DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation (CVPR 2022 · similarity 0.88)
- MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation (CVPR 2024 · similarity 0.86)
- CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image (CVPR 2025 · similarity 0.85)
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.
