Research map / 3D vision / Human pose estimation
Query6DoF: Learning Sparse Queries as Implicit Shape Prior for Category-Level 6DoF Pose Estimation
Ruiqi Wang, Xinggang Wang, Te Li, Rong Yang, Minhong Wan, Wenyu Liu
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 |
|---|---|---|---|
| replace sparse learnable queries with pre-learned point-cloud prior plus PointNet++ (ablation) | Query6DoF · REAL275 | 5°2cm: 49.0 -> 47.2 | Hurt |
| add global enhancement block (ablation) | Query6DoF · REAL275 | 5°2cm: 44.2 -> 49.0 | Improved |
| add queries deformation estimator (ablation) | Query6DoF · REAL275 | 5°2cm: 46.5 -> 49.0 | Improved |
| add query deformation and query-point correspondence estimators (ablation) | Query6DoF · REAL275 | 5°2cm: 35.4 -> 49.0 | Improved |
| regress pose directly with a pose and size estimator instead of Umeyama on Pr and Pi (ablation) | Query6DoF · REAL275 | 5°2cm: 40.0 -> 49.0 | Improved |
| increase number of queries from 64 to 1024 (ablation) | Query6DoF · REAL275 | 5°2cm: 49.0 -> 48.7 | No clear effect |
| reduce number of queries from 64 to 16 (ablation) | Query6DoF · REAL275 | 5°2cm: 49.0 -> 46.0 | Mixed |
| use sigmoid with learnable alpha instead of softmax for attention normalization (ablation) | Query6DoF · REAL275 | IoU75: 74.7 -> 76.1 | Improved |
| use sparse learnable queries as shape prior instead of SPD point-cloud prior | category-level pose estimation · REAL275 | 5°2cm: 19.3 -> 49.0 | Improved |
| add linear and non-linear shape augmentation (ablation) | Query6DoF · REAL275 | 5°2cm: 46.8 -> 49.0 | Improved |
Later papers that compared with this method
2 later accepted papers report Query6DoF as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Towards Real-World Aerial Vision Guidance With Categorical 6D Pose Tracker (TPAMI 2025 · better on 3 of 3 shared results)
- Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimation (TPAMI 2025 · better on 2 of 2 shared results)
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.
- SGPA — SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose Estimation (ICCV 2021) · better on 1 of 1 shared result
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
- PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation (ECCV 2026 · similarity 0.89)
- Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation (ECCV 2020 · similarity 0.89)
- IST-Net: Prior-Free Category-Level Pose Estimation with Implicit Space Transformation (ICCV 2023 · similarity 0.89)
- FS-Net: Fast Shape-Based Network for Category-Level 6D Object Pose Estimation With Decoupled Rotation Mechanism (CVPR 2021 · similarity 0.89)
- Category-Level 6D Object Pose and Size Estimation Using Self-Supervised Deep Prior Deformation Networks (ECCV 2022 · similarity 0.88)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.88)
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.
