Research map / 3D vision / Human pose estimation
Rotational Subgroup Voting and Pose Clustering for Robust 3D Object Recognition
Anders Glent Buch, Lilita Kiforenko, Dirk Kraft
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 rotational subgroup voting with density clustering instead of RANSAC for pose estimation | Pose clustering · Bunny sensitivity, highest noise (3.0%) | pose error: RANSAC translation error 0.048 m and rotation error 43 degrees, while pose clustering still finds the correct pose | Improved |
| use SE(3) kernel density clustering instead of PPF* approximate clustering | Pose clustering · Bin picking (Coffee cup) | recall: 0.474 -> 0.638 | Improved |
| use SE(3) kernel density clustering instead of PPF* approximate clustering | Pose clustering · Bin picking (Juice) | recall: 0.279 -> 0.449 | Improved |
| use pose clustering instead of PPF* | Pose clustering · UWA | recall: 0.936 -> 1.00 | Improved |
| use pose clustering instead of PPF* | Pose clustering · Queen's | recall: 0.992 -> 1.00 | Improved |
| use geometry-only pose clustering instead of RGB-D template method of Doumanoglou et al. | Pose clustering · Domestic data set (average) | F1: 0.803 -> 0.856 | Improved |
| use pose clustering instead of Doumanoglou et al. on a per-object basis | Pose clustering · Domestic data set (Camera) | F1: 0.903 -> 0.711 | Hurt |
| use pose clustering instead of PPF on a per-object basis | Pose clustering · Domestic data set (Shampoo) | F1: 0.651 -> 0.709 | Improved |
| increase tessellation level N_r (finer angular resolution, 60 tessellations giving 6 degrees) (ablation) | Pose clustering · design choice | performance | Improved |
Closest papers by meaning
- Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting (ECCV 2022 · similarity 0.88)
- GPV-Pose: Category-Level Object Pose Estimation via Geometry-Guided Point-Wise Voting (CVPR 2022 · similarity 0.87)
- Pose without Guesses: Generalizable Object Pose Estimation From a Single Reference (IJCV 2026 · similarity 0.87)
- A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching (TPAMI 2019 · similarity 0.87)
- Unsupervised Learning of Consensus Maximization for 3D Vision Problems (CVPR 2019 · similarity 0.86)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 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.
