Research map / 3D vision / Human pose estimation
Category-Level Articulated Object Pose Estimation
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 joint parameters predicted in NAOCS and use kinematic constraints in combined pose optimization (ablation) | NPCS pose estimation · Eyeglasses, unseen instances | rotation error: 4.0°, 7.7°, 7.2° -> 3.7° , 5.1° , 3.7° | Helped |
| add joint parameters predicted in NAOCS and use kinematic constraints in combined pose optimization (ablation) | NPCS pose estimation · Eyeglasses, unseen instances | translation error: 0.044, 0.080, 0.071 -> 0.035, 0.051, 0.057 | Helped |
| add joint parameters predicted in NAOCS and use kinematic constraints in combined pose optimization (ablation) | NPCS pose estimation · Oven, unseen instances | rotation error: 1.3° , 3.5° -> 1.1° , 2.2° | Helped |
| add joint parameters predicted in NAOCS and use kinematic constraints in combined pose optimization (ablation) | NPCS pose estimation · Washing machine, unseen instances | joint state error: 2.3 ° -> 1.00 ° | Helped |
| add joint parameters predicted in NAOCS and use kinematic constraints in combined pose optimization (ablation) | NPCS pose estimation · Laptop, unseen instances | rotation error: 11.6° , 4.4° -> 6.7° , 4.3° | Mixed |
| add joint parameters predicted in NAOCS and use kinematic constraints in combined pose optimization (ablation) | NPCS pose estimation · Drawer, unseen instances | translation error: 0.032, 0.038, 0.024, 0.025 -> 0.024, 0.021, 0.021, 0.033 | Mixed |
| predict joint parameters in NAOCS, then transform them into camera space using part poses | direct camera-space joint voting · Eyeglasses, unseen instances | joint parameter angle error: 2.9°, 15.7° -> 2.2°, 2.3° | Mixed |
| predict joint parameters in NAOCS, then transform them into camera space using part poses | direct camera-space joint voting · Oven, unseen instances | joint parameter angle error: 27.0° -> 0.8° | Helped |
| predict joint parameters in NAOCS, then transform them into camera space using part poses | direct camera-space joint voting · Laptop, unseen instances | joint parameter angle error: 29.5° -> 0.5° | Helped |
| predict joint parameters in NAOCS, then transform them into camera space using part poses | direct camera-space joint voting · Oven, unseen instances | joint parameter distance error: 0.024 -> 0.024 | No clear effect |
Closest papers by meaning
- CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image (CVPR 2025 · similarity 0.90)
- EfficientCAPER: An End-to-End Framework for Fast and Robust Category-Level Articulated Object Pose Estimation (NeurIPS 2024 · similarity 0.89)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.89)
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · similarity 0.88)
- Emergence of a Shared Canonical Object Frame from In-the-Wild Videos (NeurIPS 2026 · similarity 0.88)
- Universal Features Guided Zero-Shot Category-Level Object Pose Estimation (AAAI 2025 · 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.