Research map / 3D vision / Human pose estimation
Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting
Yangzheng Wu, Mohsen Zand, Ali Etemad, Michael Greenspan
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 radial (1D) voting instead of polar (2D) voting (ablation) | keypoint voting · LINEMOD ape/driller/eggbox, FPS keypoints | keypoint localization error: 1.9-4.3x more accurate than polar | Improved |
| use radial voting instead of offset voting for dispersed keypoints (ablation) | keypoint voting · LINEMOD ape, disperse keypoints | keypoint localization error (mm): 10.4 -> 1.8 | Improved |
| reduce voting dimensionality via polar (2D) parametrization of vector (3D) (ablation) | vector voting · LINEMOD | keypoint localization error: 1.7-2.4x greater accuracy | Improved |
| disperse keypoints (increase mean keypoint distance) for offset voting (ablation) | offset voting · LINEMOD ape | keypoint localization error (mm): 5.8 -> 10.4 | Hurt |
| disperse keypoints (increase mean keypoint distance) for radial voting (ablation) | radial voting · LINEMOD ape | keypoint localization error (mm): 2.2 -> 2.7 | Hurt |
| disperse keypoints to about 2x object radius under fixed localization error (ablation) | transformation estimation · Occlusion LINEMOD simulation | transformation error (ADD): scale factor 1 to 5; error plateaus after scale 3 or 4 | Improved |
| disperse keypoints to 2x radius in full RCVPose (ablation) | RCVPose · Occlusion LINEMOD | ADD(s): 4 of 8 objects and the average higher at 2x | Mixed |
| add ICP refinement | RCVPose · Occlusion LINEMOD | ADD(s) %: 70.2 -> 71.1 | Improved |
| add ICP refinement | RCVPose · LINEMOD | ADD(s) %: 99.4 -> 99.7 | Improved |
| add ICP refinement | RCVPose · YCB-Video | ADD(s) %: 95.2 -> 95.9 | Improved |
| add ICP refinement | RCVPose · YCB-Video | AUC %: 96.6 -> 97.2 | Improved |
| train one shared network for all 3 keypoints instead of separate networks (ablation) | RCVPose · LINEMOD | accuracy | Hurt |
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.
- PVN3D — PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation (CVPR 2020) · better on 4 of 4 shared results
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 Object Pose Estimation (TPAMI 2020 · similarity 0.90)
- PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation (CVPR 2019 · similarity 0.90)
- PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation (CVPR 2020 · similarity 0.90)
- Rotational Subgroup Voting and Pose Clustering for Robust 3D Object Recognition (ICCV 2017 · similarity 0.88)
- ProbPose: A Probabilistic Approach to 2D Human Pose Estimation (CVPR 2025 · similarity 0.86)
- Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features (NeurIPS 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.
