Research map / 3D vision / Human pose estimation
A Graph-Based Approach for Category-Agnostic Pose Estimation
Or Hirschorn, Shai Avidan
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 |
|---|---|---|---|
| replace decoder MLP FFN with graph-based FFN using the skeleton graph | CapeFormer-T · MP-100 1-shot | PCK@0.2: 86.25 -> 87.23 | Improved |
| replace decoder MLP FFN with graph-based FFN using the skeleton graph | CapeFormer-T · MP-100 5-shot | PCK@0.2: 90.90 -> 91.16 | Improved |
| swap ResNet-50 for SwinV2-T, remove keypoint positional encoding, lower-variance Gaussian keypoint mask (ablation) | CapeFormer · MP-100 1-shot | PCK@0.2: 85.31 -> 86.25 | Improved |
| use keypoint positional encoding (Support Keypoint Identifier) on original keypoint order (ablation) | CapeFormer · MP-100 | PCK: 85.24 -> 89.26 | Improved |
| shuffle keypoint order at test time with keypoint positional encoding (ablation) | CapeFormer · MP-100 | PCK: 89.26 -> 64.20 | Hurt |
| add graph FFN in place of positional encoding (ablation) | CapeFormer without PE · MP-100 | PCK: 85.24 -> 87.71 | Improved |
| use a fully connected or edge-less graph instead of the pose graph (ablation) | GraphCape · MP-100 1-shot Split 1 | PCK@0.2: 91.19 -> 89.35 | Hurt |
| use random graphs per instance instead of the pose graph (ablation) | GraphCape · MP-100 1-shot Split 1 | PCK@0.2: 91.19 -> 81.49 | Hurt |
| use graph decoder when support or query images are partially masked (ablation) | GraphCape · MP-100 split 1 masking | PCK | Improved |
Closest papers by meaning
- CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation (ICLR 2025 · similarity 0.96)
- Meta-Point Learning and Refining for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.92)
- ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.91)
- Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation (CVPR 2024 · similarity 0.88)
- Universal Features Guided Zero-Shot Category-Level Object Pose Estimation (AAAI 2025 · similarity 0.88)
- Rethinking Correspondence-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.88)
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.
