Research map / 3D vision / Human pose estimation
RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation
Ruida Zhang, Yan Di, Zhiqiang Lou, Fabian Manhardt, Federico Tombari, Xiangyang Ji
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 |
|---|---|---|---|
| add direct DVPB prediction (E1 to E2) (ablation) | RBP-Pose · REAL275 | 5deg2cm: 0.8% under 5deg2cm | Improved |
| add direct DVPB prediction (E1 to E2) (ablation) | RBP-Pose · REAL275 | 5deg5cm: +2.1% in 5deg5cm | Improved |
| predict SPRV with shape-prior hypothesis (E1 to E3) (ablation) | RBP-Pose · REAL275 | 5deg2cm: 2.6% under 5deg2cm and 2.5% under 10deg2cm up; 5deg5cm and 10deg5cm decrease | Mixed |
| add consistency loss between SPRV and pose (E3 to E7) (ablation) | RBP-Pose · REAL275 | 5deg2cm: 36.0 -> 38.2 | Improved |
| add consistency loss between SPRV and pose (E3 to E7) (ablation) | RBP-Pose · REAL275 | IoU75: 67.7 -> 67.8 | Improved |
| add consistency loss between SPRV and pose (E3 to E7) (ablation) | RBP-Pose · REAL275 | 5deg5cm: 44.5 -> 48.1 | Improved |
| enforce consistency on DVPB without residual reasoning (E4) (ablation) | RBP-Pose · REAL275 | IoU75: 67.8 -> 66.2 | Hurt |
| add non-linear shape augmentation (E5 to E7) (ablation) | RBP-Pose · REAL275 | 5deg2cm: drops by 15.6% and 18.4% | Improved |
| add non-linear shape augmentation (E5 to E7) (ablation) | RBP-Pose · REAL275 | 5deg5cm: 29.7 -> 48.1 | Improved |
| non-linear instead of linear shape augmentation (E6 to E7) (ablation) | RBP-Pose · REAL275 | IoU75: 66.2 -> 67.8 | Improved |
| non-linear instead of linear shape augmentation (E6 to E7) (ablation) | RBP-Pose · REAL275 | 5deg2cm: 36.1 -> 38.2 | Improved |
| RBP-Pose vs GPV-Pose | GPV-Pose · REAL275 | 5deg2cm: 32.0 -> 38.2 | Improved |
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 9 of 11 shared results
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
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · similarity 0.86)
- GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.83)
- Dynamic Support Information Mining for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.83)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.83)
- R^2-Art: Category-Level Articulation Pose Estimation from Single RGB Image via Cascade Render Strategy (AAAI 2025 · similarity 0.83)
- Universal Features Guided Zero-Shot Category-Level Object Pose Estimation (AAAI 2025 · similarity 0.82)
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.
