Research map / 3D vision / Human pose estimation
GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation
Jiyong Rao, Yu Wang, Shengjie Zhao
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 KL regularization on posterior (ablation) | GenCape-T · MP-100 Split-1 1-shot | PCK@0.2: 91.19 -> 91.43 | Improved |
| add sparsity loss on top of KL (ablation) | GenCape-T · MP-100 Split-1 1-shot | PCK@0.2: 91.43 -> 91.75 | Improved |
| add Compositional Graph Transfer (ablation) | GenCape-T · MP-100 Split-1 1-shot | PCK@0.2: 91.75 -> 92.05 | Improved |
| use iterative layer-wise structure refinement (ablation) | GenCape-T · MP-100 Split-1 1-shot | PCK@0.2: 91.48 -> 92.05 | Improved |
| use learned adjacency instead of self-attention weights (ablation) | GenCape-T · MP-100 Split-1 1-shot | PCK@0.2: 89.33 -> 92.05 | Improved |
| use learned graph rather than random initialized graph (ablation) | GenCape-T · MP-100 Split-1 1-shot | PCK@0.2: 84.39 -> 92.05 | Improved |
| impose symmetry on learned adjacency (ablation) | GenCape-T · MP-100 Split-1 1-shot | PCK@0.2: 91.71 -> 92.05 | Improved |
| query weighting across layers plus Bayesian fusion across samples vs same strategy at both (ablation) | GenCape-T · MP-100 Split-1 1-shot | PCK@0.2: 91.74 -> 92.05 | Improved |
| increase latent dimension from 32 to 128 (ablation) | GenCape-T · MP-100 Split-1 1-shot | PCK@0.2: 92.05 -> 91.40 | Hurt |
| use 3 posterior samples rather than 2 or 5 (ablation) | GenCape-T · MP-100 Split-1 1-shot | PCK@0.2: 91.60 / 91.63 -> 92.05 | Improved |
| use GenCape instead of GraphCape for cross-supercategory transfer | GenCape · Cross super-category / Furniture->HumanBody | PCK@0.2: Felidae->Person 56.26 -> 68.08; Furniture->HumanBody 73.79 -> 73.09 | Mixed |
| use GenCape on 1-shot MP-100 instead of GraphCape | GenCape-T · MP-100 1-shot avg | PCK@0.2: 87.23 -> 88.09 | Improved |
Later papers that compared with this method
1 later accepted paper reports GenCape as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Occlusion-Resilient Category-Agnostic Pose Estimation with Conditional Flow Matching (ECCV 2026 · better on 3 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SCAPE — SCAPE: A Simple and Strong Category-Agnostic Pose Estimator (ECCV 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation (ICLR 2025 · similarity 0.90)
- ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.90)
- Meta-Point Learning and Refining for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.89)
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · similarity 0.87)
- Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation (CVPR 2025 · similarity 0.87)
- GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking (NeurIPS 2026 · 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.
