Research map / 3D vision / Human pose estimation
Zero-Shot Category-Level Object Pose Estimation
Walter Goodwin, Sagar Vaze, Ioannis Havoutis, Ingmar Posner
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 |
|---|---|---|---|
| use semantic-correspondence method instead of SWaV baseline | zero-shot pose estimation · CO3D (20 categories, 5 target views) | Acc30: 7.5 -> 46.3 | Improved |
| add fine rigid-body alignment with depth on top of best view (ablation) | Ours-BV · CO3D (20 categories, 5 target views) | Acc30: 35.4 -> 46.3 | Improved |
| use cyclical distance instead of optimal transport for correspondences (ablation) | Ours · CO3D (20 categories, 5 target views) | Acc30: 44.8 -> 46.3 | Improved |
| use cyclical distance instead of dual softmax for correspondences (ablation) | Ours · CO3D (20 categories, 5 target views) | Acc30: 44.5 -> 46.3 | Improved |
| increase K from 30 to 50 correspondences (ablation) | Ours · CO3D (20 categories, 5 target views) | Acc30: 43.5 -> 46.3 | Improved |
| increase RANSAC trials from 500 to 1000 (ablation) | Ours · CO3D (20 categories, 5 target views) | Acc30: 45.8 -> 46.3 | Improved |
| increase RANSAC trials from 1000 to 2000 (ablation) | Ours · CO3D (20 categories, 5 target views) | Acc30: 46.3 -> 46.6 | No clear effect |
| double target views from 5 to 10 (ablation) | Ours · CO3D (20 categories, 5 target views) | Acc30: over 6% | Improved |
| estimate pose via essential matrix instead of depth rigid transform (ablation) | Ours-BV · CO3D (20 categories, 5 target views) | Acc30 | Hurt |
Closest papers by meaning
- Universal Features Guided Zero-Shot Category-Level Object Pose Estimation (AAAI 2025 · similarity 0.90)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.89)
- NOPE: Novel Object Pose Estimation from a Single Image (CVPR 2024 · similarity 0.88)
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · similarity 0.88)
- GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking (NeurIPS 2026 · similarity 0.88)
- Vision Foundation Model Enables Generalizable Object Pose Estimation (NeurIPS 2024 · 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.
