Research map / 3D vision / Human pose estimation
SE(3)-Equivariance with Geometric and Topological Guidance for Category-Level Object Pose Estimation
Sheng Yu, Di-Hua Zhai, Yuanqing Xia
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 |
|---|---|---|---|
| add topology guidance and SE(3)-equivariance modules to geometry-only baseline (ablation) | SEGPose · REAL275 | 5deg5cm: 51.1 -> 61.1 | Improved |
| add topology-guided point cloud reconstruction (ablation) | SEGPose · REAL275 | 5deg5cm: 58.1 -> 61.1 | Improved |
| add SE(3)-equivariance guided pose estimation head (ablation) | SEGPose · REAL275 | 5deg5cm: 60.3 -> 61.1 | Improved |
| add input data augmentation (ablation) | SEGPose · REAL275 | 5deg5cm: 60.7 -> 61.1 | Improved |
| add topology module versus SE(3) module alone (ablation) | SEGPose · REAL275 | mAP | Improved |
| add SDF-based bounding box-pose consistency loss Lsdf (ablation) | SEGPose · REAL275 | mAP | Improved |
| use SEGPose instead of HS-Pose (depth-based) | category-level pose estimation · Wild6D | 5deg5cm: 28.6 -> 35.6 | Improved |
| use SEGPose instead of HS-Pose in robot grasping | UR3 grasping · Single-object grasping | grasp success rate (%): 75.6 -> 88.9 | Improved |
| use depth-only SEGPose versus RGB-D SpotPose | REAL275 · REAL275 | 5deg5cm: 64.8 -> 61.1 | Hurt |
Closest papers by meaning
- Leveraging SE(3) Equivariance for Self-supervised Category-Level Object Pose Estimation from Point Clouds (NeurIPS 2021 · similarity 0.91)
- SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation (CVPR 2024 · similarity 0.88)
- Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks (ICLR 2024 · similarity 0.87)
- Vision Foundation Model Enables Generalizable Object Pose Estimation (NeurIPS 2024 · similarity 0.86)
- Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimation (ICLR 2025 · similarity 0.86)
- Rethinking Correspondence-based Category-Level Object Pose Estimation (CVPR 2025 · 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.
