Research map / 3D vision / Human pose estimation
DualPoseNet: Category-Level 6D Object Pose and Size Estimation Using Dual Pose Network With Refined Learning of Pose Consistency
Jiehong Lin, Zewei Wei, Zhihao Li, Songcen Xu, Kui Jia, Yuanqing Li
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 implicit pose decoder as auxiliary supervision (ablation) | DualPoseNet · REAL275 | mAP IoU50 10deg 10%: 37.3 -> 43.1 | Improved |
| add implicit pose decoder as auxiliary supervision (ablation) | DualPoseNet · REAL275 | mAP IoU75 5deg 10%: 19.7 -> 23.8 | Improved |
| add refined learning of pose consistency at test time (ablation) | DualPoseNet · REAL275 | mAP IoU75: 60.1 -> 62.2 | Improved |
| add refined learning of pose consistency at test time (ablation) | DualPoseNet · REAL275 | mAP 10deg 5cm: 64.2 -> 66.8 | Improved |
| use spherical fusion encoder instead of SCNN early fusion (ablation) | DualPoseNet · REAL275 | mAP IoU50 10deg 10%: 35.5 -> 43.1 | Improved |
| use spherical fusion encoder instead of SCNN late fusion (ablation) | DualPoseNet · REAL275 | mAP IoU50 10deg 10%: 41.7 -> 43.1 | Improved |
| use spherical fusion encoder instead of Densefusion (ablation) | DualPoseNet · REAL275 | mAP IoU50 10deg 10%: 17.4 -> 43.1 | Improved |
| add implicit decoder (ablation) | DualPoseNet · YCB-Video | ADD-S AUC: 90.5 -> 91.2 | Improved |
| add refined learning of pose consistency (ablation) | DualPoseNet · YCB-Video | ADD-S AUC: 91.2 -> 93.3 | Improved |
| add iterative residual pose refinement (ablation) | DualPoseNet · YCB-Video | ADD-S AUC: 91.2 -> 95.0 | Improved |
| use a larger fine-tuning learning rate in pose consistency refinement (ablation) | DualPoseNet · REAL275 | mAP IoU50 10deg 20% | Mixed |
Later papers that compared with this method
7 later accepted papers report DualPoseNet as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations (ICCV 2023 · better on 1 of 1 shared result)
- Category-Level 6D Object Pose and Size Estimation Using Self-Supervised Deep Prior Deformation Networks (ECCV 2022 · better on 4 of 4 shared results)
- Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset (NeurIPS 2022 · better on 3 of 3 shared results)
- CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild (CVPR 2022 · better on 0 of 1 shared result)
- GPV-Pose: Category-Level Object Pose Estimation via Geometry-Guided Point-Wise Voting (CVPR 2022 · better on 0 of 1 shared result)
- CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement (ECCV 2022 · better on 1 of 1 shared result)
- Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space (NeurIPS 2021 · better on 4 of 6 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
- DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-Scale Consistency (CVPR 2021 · similarity 0.91)
- SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation (CVPR 2024 · similarity 0.90)
- GDRNPP: A Geometry-Guided and Fully Learning-Based Object Pose Estimator (TPAMI 2025 · similarity 0.89)
- Pose without Guesses: Generalizable Object Pose Estimation From a Single Reference (IJCV 2026 · similarity 0.89)
- Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval (CVPR 2024 · 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.
