Research map / 3D vision / Human pose estimation
Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation
Dengsheng Chen, Jun Li, Zheng Wang, Kai Xu
Check 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 canonical shape space codes in pose and size estimation (ablation) | CASS · NOCS-REAL275 | 5°5cm mAP: 4.2 -> 23.5 | Improved |
| Use batch mixing to align RGBD and canonical-shape feature distributions (ablation) | CASS · NOCS-REAL275 | 5°5cm mAP: 4.7 -> 23.5 | Improved |
| Share feature-extractor weights for distribution matching (ablation) | CASS · NOCS-REAL275 | 5°5cm mAP: 8.4 -> 23.5 | Improved |
| Use a VAE rather than an AE to model the canonical shape space (ablation) | CASS · NOCS-REAL275 | 5°5cm mAP: 17.0 -> 23.5 | Improved |
| Use batch mixing (ablation) | CASS RGBD-to-shape reconstruction · NOCS-REAL275 overall | CD: 2.33 -> 1.06 | Improved |
| Use batch mixing (ablation) | CASS RGBD-to-shape reconstruction · NOCS-REAL275 overall | EMD: 0.16 -> 0.05 | Improved |
| Use CASS correspondence-free pose estimation instead of NOCS correspondence-based estimation | NOCS-REAL275 pose and size estimation · NOCS-REAL275 | 10°5cm mAP: 43.7 -> 58.0 | Improved |
| Use CASS correspondence-free pose estimation instead of NOCS correspondence-based estimation | NOCS-REAL275 pose and size estimation · NOCS-REAL275 | IoU25 mAP: 84.4 -> 84.2 | Hurt |
Closest papers by meaning
- Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation (ECCV 2020 · similarity 0.91)
- CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image (CVPR 2025 · similarity 0.87)
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · similarity 0.87)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.87)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.87)
- GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation (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.
