Research map / 3D vision / Human pose estimation
Learning Deep Network for Detecting 3D Object Keypoints and 6D Poses
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 |
|---|---|---|---|
| add the distinctiveness loss (ablation) | OK-POSE · LINEMOD | ADD: 15.8 -> 35.8 | Helped |
| add the depth regression loss (ablation) | OK-POSE · LINEMOD | ADD: 6.7 -> 35.8 | Helped |
| add the cross-view consistency loss (ablation) | OK-POSE · LINEMOD | ADD: 8.5 -> 35.8 | Helped |
| add the separation loss (ablation) | OK-POSE · LINEMOD | ADD: 24.9 -> 35.8 | Helped |
| add the transformation recovery loss (ablation) | OK-POSE · LINEMOD | ADD: 23.3 -> 35.8 | Helped |
| use 3 references instead of 1 (ablation) | OK-POSE · ape sequence | ADD: 35.8 -> 38.0 | Helped |
| use 9 references instead of 1 (ablation) | OK-POSE · ape sequence | ADD: 35.8 -> 39.84 | Helped |
| learn keypoints from real image pairs with relative viewpoint transformation rather than synthetic CAD-rendered training images | 6D object pose estimation · LINEMOD | ADD mean: 8.4 -> 30.16 | Helped |
| use OK-POSE rather than keypointnet with detected bounding boxes | 6D object pose estimation · OCCLUSION | MAP: 0.13 -> 0.47 | Helped |
Closest papers by meaning
- Keypoint-Graph-Driven Learning Framework for Object Pose Estimation (CVPR 2021 · similarity 0.92)
- KeyPose: Category-Level 6D Object Pose Estimation with Self-Adaptive Keypoints (AAAI 2025 · similarity 0.89)
- Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation (CVPR 2024 · similarity 0.89)
- Open-Vocabulary Object 6D Pose Estimation (CVPR 2024 · similarity 0.88)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.87)
- FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects (CVPR 2024 · similarity 0.87)
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.