Research map / 3D vision / Human pose estimation
CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement
Xingyu Liu, Gu Wang, Yi Li, 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 |
|---|---|---|---|
| use mean shape prior instead of 3D bounding box (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 47.2 -> 54.4 | Improved |
| use mean shape prior instead of 3D axes (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 43.1 -> 54.4 | Improved |
| add focalization to origin (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 47.5 -> 54.4 | Improved |
| add adaptive points sampling (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 42.3 -> 54.4 | Improved |
| use PointNet instead of 3D-GCN (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 43.4 -> 54.4 | Improved |
| add weight sharing between the two branches (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 2.0 -> 54.4 | Improved |
| use disentangled heads instead of a single TS-Head style head (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 46.2 -> 54.4 | Improved |
| use disentangled heads instead of a single Rot-Head style head (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 50.0 -> 54.4 | Improved |
| add pose-matching loss L_pm (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 50.7 -> 54.4 | Improved |
| add separate rotation, translation and size losses (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 30.1 -> 54.4 | Improved |
| also feed MaxPool(F_p) to TS-Head (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 54.4 -> 52.8 | Hurt |
| add occlusion to the input (ablation) | CATRE · REAL275 (SPD* init) | 5deg5cm accuracy: 54.4 -> 38.6 | Hurt |
Later papers that compared with this method
2 later accepted papers report CATRE as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking (ECCV 2024 · better on 0 of 3 shared results)
- Generative Category-level Object Pose Estimation via Diffusion Models (NeurIPS 2023 · better on 1 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- SGPA — SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose Estimation (ICCV 2021) · better on 3 of 3 shared results
- CAPTRA — CAPTRA: CAtegory-Level Pose Tracking for Rigid and Articulated Objects From Point Clouds (ICCV 2021) · better on 2 of 3 shared results
- DualPoseNet — DualPoseNet: Category-Level 6D Object Pose and Size Estimation Using Dual Pose Network With Refined Learning of Pose Consistency (ICCV 2021) · better on 1 of 1 shared result
- DenseFusion — DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion (CVPR 2019) · 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
- GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement (CVPR 2024 · similarity 0.92)
- CatFormer: Category-Level 6D Object Pose Estimation with Transformer (AAAI 2024 · similarity 0.89)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.88)
- Rethinking Correspondence-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.87)
- SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation (CVPR 2024 · 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.
