Research map / 3D vision / Human pose estimation
Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild
Read the paperCheck 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 cross-instance and cross-time cycle-consistency losses (ablation) | CSE correspondence training · Wild6D | IOU_0.5: +5.2 | Helped |
| add cross-time and cross-instance cycle losses (both levels) vs none (ablation) | Laptop category · Wild6D laptop | 5deg 5cm mAP: 10.2 to 16.0 | Helped |
| add cross-instance and cross-time cycle losses (ablation) | keypoint transfer · CUB-200-2011 | PCK: 33.9 to 64.5 | Helped |
| add depth loss (ablation) | CSE training · Wild6D | IOU_0.5: 52.6 to 68.2 | Helped |
| solve pose from CSE correspondences instead of regressing pose (ablation) | pose estimation · Wild6D | IOU_0.5: 32.0 to 68.2 | Helped |
| use surface embedding (mesh encoder) for correspondence (ablation) | pose estimation · Wild6D | IOU_0.5: 57.1 to 68.2 | Helped |
| add shape deformation of canonical mesh (ablation) | pose estimation · Wild6D | IOU_0.5: 55.3 to 68.2 | Helped |
| self-supervised training directly on Wild6D (no sim, no 3D labels) | category-level pose estimation · Wild6D | 5deg 2cm and 10deg 2cm: +3.2 and +3.3 over RePoNet | Helped |
| self-supervised training on Wild6D | category-level pose estimation · Wild6D | IOU_0.5: 68.2 vs RePoNet 70.3 | Hurt |
| learn CSE with cycle losses instead of CSM-style direct mapping | keypoint transfer · CUB-200-2011 | PCK: 64.5 vs 45.8 (CSM) | Helped |
Closest papers by meaning
- Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset (NeurIPS 2022 · similarity 0.92)
- Emergence of a Shared Canonical Object Frame from In-the-Wild Videos (NeurIPS 2026 · similarity 0.90)
- Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation (CVPR 2024 · similarity 0.89)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.89)
- CatFormer: Category-Level 6D Object Pose Estimation with Transformer (AAAI 2024 · similarity 0.87)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 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.