Research map / Detection and segmentation / CNN features
Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation
Min Shi, Zihao Huang, Xianzheng Ma, Xiaowei Hu, Zhiguo Cao
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 one-stage matching with a two-stage proposal refinement decoder (ablation) | CapeFormer · MP-100 split 1 test, 1-shot | PCK: 85.32 -> 89.45 | Improved |
| add query-support joint refine encoder instead of DETR encoder (ablation) | CapeFormer · MP-100 split 1 test, 1-shot | PCK: 80.32 -> 82.86 | Improved |
| add fixed sinusoidal support keypoint identifier (ablation) | CapeFormer · MP-100 split 1 test, 1-shot | PCK: 82.86 -> 85.32 | Improved |
| use heatmap supervision together with expectation loss (ablation) | CapeFormer similarity loss · MP-100 split 1 test, 1-shot | PCK: 88.74 -> 89.45 | Improved |
| remove expectation loss and use heatmap supervision only (ablation) | CapeFormer similarity loss · MP-100 split 1 test, 1-shot | PCK: 89.45 -> 88.74 | Hurt |
| remove heatmap loss and use expectation supervision only (ablation) | CapeFormer similarity loss · MP-100 split 1 test, 1-shot | PCK: 89.41 -> 89.45 | No clear effect |
| replace fixed sinusoidal identifier with learnable embedding (ablation) | CapeFormer · MP-100 split 1 test, 1-shot | PCK: 89.45 -> 88.96 | Hurt |
| use CapeFormer instead of POMNet | MP-100 · 1-shot, Average | PCK: 79.70 -> 85.31 | Improved |
| use CapeFormer instead of POMNet | MP-100 · 5-shot, Average | PCK: 80.71 -> 89.30 | Improved |
| increase support examples from 1-shot to 5-shot | CapeFormer · MP-100, Average | PCK: 85.31 -> 89.30 | Improved |
| use CapeFormer instead of POMNet | MP-100 cross-super-category · 1-shot Vehicle | PCK: 34.92 -> 45.40 | Improved |
Closest papers by meaning
- CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation (ICLR 2025 · similarity 0.93)
- ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.93)
- Meta-Point Learning and Refining for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.92)
- Rethinking Correspondence-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.89)
- 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)
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.
