Research map / 3D vision / Human pose estimation
PVNet: Pixel-Wise Voting Network for 6DoF Object Pose Estimation
Sida Peng, Xiaowei Zhou, Yuan Liu, Haotong Lin, Qixing Huang, Hujun Bao
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 |
|---|---|---|---|
| use pixel-wise voting keypoint localization instead of coordinate regression (Tekin) (ablation) | PVNet · Occlusion LINEMOD | ADD(-S) accuracy: 6.42 -> 33.88 | Improved |
| use FPS surface keypoints instead of bounding-box corners (ablation) | PVNet · Occlusion LINEMOD | ADD(-S) accuracy: 33.88 -> 39.76 | Improved |
| increase FPS keypoints from 4 to 8 (ablation) | PVNet · Occlusion LINEMOD | ADD(-S) accuracy: 17.96 -> 39.76 | Improved |
| increase FPS keypoints from 8 to 12 (ablation) | PVNet · Occlusion LINEMOD | ADD(-S) accuracy: 39.76 -> 39.92 | No clear effect |
| add uncertainty-driven PnP instead of EPnP (ablation) | PVNet FPS 8 · Occlusion LINEMOD | ADD(-S) accuracy: 39.76 -> 40.77 | Improved |
| PVNet versus BB8 without refinement | PVNet · LINEMOD | 2D projection accuracy: 83.9 -> 99.00 | Improved |
| PVNet versus Tekin on ADD(-S) | PVNet · LINEMOD | ADD(-S) accuracy: 55.95 -> 86.27 | Improved |
| PVNet versus SSD-6D with refinement | PVNet · LINEMOD | ADD(-S) accuracy: 79 -> 86.27 | Improved |
| PVNet versus Oberweger on 2D projection | PVNet · Occlusion LINEMOD | 2D projection accuracy: 60.9 -> 61.06 | No clear effect |
| PVNet versus Oberweger on ADD(-S) | PVNet · Occlusion LINEMOD | ADD(-S) accuracy: 30.4 -> 40.77 | Improved |
| PVNet versus Oberweger on ADD(-S) AUC | PVNet · YCB-Video | ADD(-S) AUC: 72.8 -> 73.4 | 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.
- SSD-6D — SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again (ICCV 2017) · 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
- PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation (CVPR 2019 · similarity 0.99)
- PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation (CVPR 2020 · similarity 0.91)
- Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting (ECCV 2022 · similarity 0.90)
- CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation (ICCV 2019 · similarity 0.89)
- Single-Stage 6D Object Pose Estimation (CVPR 2020 · similarity 0.88)
- Segmentation-Driven 6D Object Pose Estimation (CVPR 2019 · 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.
