Research map / 3D vision / Human pose estimation
CPPF++: Uncertainty-Aware Sim2Real Object Pose Estimation by Vote Aggregation
Yang You, Wenhao He, Jin Liu, Hongkai Xiong, Weiming Wang, Cewu Lu
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 5-point tuples instead of point pairs (N=2) (ablation) | CPPF++ · NOCS REAL275 | mAP 5deg 5cm: 28.7 -> 32.3 | Improved |
| increase tuple size from 5 to 10 (ablation) | CPPF++ · NOCS REAL275 | mAP 5deg 5cm: 32.3 -> 32.2 (15deg 5cm: 85.2 -> 83.1) | No clear effect |
| add uncertainty modeling of voting targets (ablation) | CPPF++ · NOCS REAL275 | mAP 5deg 5cm: 24.2 -> 32.3 | Improved |
| add noisy pair filtering (ablation) | CPPF++ · NOCS REAL275 | mAP 5deg 5cm: 12.6 -> 32.3 | Improved |
| add importance point re-weighting (ablation) | CPPF++ · NOCS REAL275 | mAP 5deg 5cm: 31.0 -> 32.3 | Improved |
| add online alignment optimization (ablation) | CPPF++ · NOCS REAL275 | mAP 5deg 5cm: 24.5 -> 32.3 (+7.8 AP@5deg 5cm) | Improved |
| use ensemble of geometric and visual models instead of geometric only (ablation) | CPPF++ · NOCS REAL275 | mAP 5deg 5cm: 19.8 -> 32.3 | Improved |
| use ensemble of geometric and visual models instead of visual only (ablation) | CPPF++ · NOCS REAL275 | mAP 5deg 5cm: 22.1 -> 32.3 | Improved |
| use model-switching ensemble instead of concatenating geometric and visual features (ablation) | CPPF++ · NOCS REAL275 | mAP 5deg 5cm: 18.2 -> 32.3 | Improved |
| use GroundedSAM detector instead of DualPoseNet masks | CPPF++ · NOCS REAL275 | mAP 3D25 / 10deg 5cm: 3D25: 82.4 -> 72.7; 10deg 5cm: 65.9 -> 72.0 | Mixed |
| add ICP refinement | CPPF++ · YCB-Video | ADD(-S) AUC: 55.4 -> 70.0 | Improved |
| use zero-shot/CLIP instance detector instead of PoseCNN masks | CPPF++ · YCB-Video | ADD(-S) AUC: 55.4 -> 46.8 | 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.
- CPPF — CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild (CVPR 2022) · better on 6 of 6 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
- CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild (CVPR 2022 · similarity 0.89)
- Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis (NeurIPS 2024 · similarity 0.86)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.86)
- Object Pose Estimation via the Aggregation of Diffusion Features (CVPR 2024 · similarity 0.85)
- UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References (CVPR 2025 · similarity 0.85)
- LEAP: Liberate Sparse-View 3D Modeling from Camera Poses (ICLR 2024 · 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.
