Research map / 3D vision / Human pose estimation
PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation
Yihan Chen, Huan Ren, Wenfei Yang, Hang Du, Tianzhu Zhang, Feng Wu
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 the category prior branch with joint deformation and alignment (ablation) | PriorPose · REAL275 | mAP 5deg5cm: 64.4 -> 68.2 | Improved |
| couple deformation and alignment jointly instead of serial deform-then-align (ablation) | PriorPose · REAL275 | mAP 5deg5cm: 64.5 -> 68.2 | Improved |
| use structured mean-shape prior instead of Gaussian prior (ablation) | PriorPose · REAL275 | mAP 5deg5cm: 65.3 -> 68.2 | Improved |
| add shape-consistency losses (ablation) | PriorPose · REAL275 | mAP 5deg5cm: 65.5 -> 68.2 | Improved |
| add reconstruction loss with deformation head (ablation) | PriorPose · REAL275 | mAP 5deg2cm: 58.1 -> 60.2 | Improved |
| add canonical-space consistency to reconstruction loss (ablation) | PriorPose · REAL275 | mAP 5deg5cm: 65.5 -> 65.9 | Improved |
| add camera-space consistency to reconstruction loss (ablation) | PriorPose · REAL275 | mAP 10deg2cm: 80.7 -> 79.8 | Mixed |
| combine canonical and camera consistency (ablation) | PriorPose · REAL275 | mAP 5deg5cm: 65.5 -> 68.2 | Improved |
| use seeded fusion instead of dense self-attention (ablation) | PriorPose · REAL275 | mAP 5deg5cm: 66.5 -> 68.2 | Improved |
| add geometry-quality bias (gamma=0.2) (ablation) | PriorPose · REAL275 | mAP 5deg5cm: 66.4 -> 68.2 | Improved |
| reduce kNN size from 32 to 16 (ablation) | PriorPose · REAL275 | mAP 10deg5cm: 88.9 -> 86.2 | Hurt |
| increase kNN size from 32 to 64 (ablation) | PriorPose · REAL275 | mAP 5deg5cm: 68.2 -> 67.1 | Hurt |
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.
- GCE-Pose — GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation (CVPR 2025) · better on 4 of 4 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
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.91)
- GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement (CVPR 2024 · similarity 0.91)
- Rethinking Correspondence-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.91)
- SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation (CVPR 2024 · similarity 0.90)
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · similarity 0.90)
- CatFormer: Category-Level 6D Object Pose Estimation with Transformer (AAAI 2024 · similarity 0.90)
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.
