Research map / 3D vision / Human pose estimation
ZebraPose: Coarse To Fine Surface Encoding for 6DoF Object Pose Estimation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 ZebraPose instead of SO-Pose | RGB pose estimation · LM-O | average recall ADD(-S) (%): 62.3 -> 76.9 | Helped |
| Use ZebraPose instead of FFB6D | pose estimation · LM-O | average recall ADD(-S) (%): 66.2 -> 76.9 | Helped |
| Use ZebraPose instead of RePose | pose estimation · YCB-V | ADD(-S) (%): 62.1 -> 80.5 | Helped |
| Use ZebraPose instead of GDR-Net | pose estimation · YCB-V | AUC of ADD(-S) (%): 91.6 -> 90.1 | Hurt |
| Use ZebraPose instead of CosyPose | pose estimation · YCB-V | AUC of ADD(-S) (%): 84.5 -> 85.3 | Helped |
| Use radix 2 instead of radix 256 with Progressive-X (ablation) | ZebraPose · LM-O | average recall ADD(-S) (%): 74.52 -> 75.23 | Helped |
| Use Progressive-X instead of RANSAC/PnP with radix 2 (ablation) | ZebraPose · LM-O | average recall ADD(-S) (%): 73.06 -> 75.23 (+2.17) | Helped |
| Add hierarchical learning (ablation) | ZebraPose with radix 2 · LM-O | average recall ADD(-S) (%): 75.23 -> 75.86 | Helped |
| Replace Faster R-CNN with FCOS (ablation) | ZebraPose with hierarchical learning · LM-O | average recall ADD(-S) (%): 75.86 -> 76.91 | Helped |
| Use the full 16-bit code rather than omit redundant final bits (ablation) | ZebraPose · LM-O | pose accuracy | Mixed |
| Use RANSAC/PnP rather than Progressive-X (ablation) | ZebraPose · LM-O | average recall: about 2.6% | Hurt |
Closest papers by meaning
- HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation (CVPR 2024 · similarity 0.90)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.87)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.87)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · similarity 0.87)
- Co-op: Correspondence-based Novel Object Pose Estimation (CVPR 2025 · similarity 0.86)
- FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects (CVPR 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.