Research map / 3D vision / Human pose estimation
RNNPose: Recurrent 6-DoF Object Pose Refinement With Robust Correspondence Field Estimation and Pose Optimization
Yan Xu, Kwan-Yee Lin, Guofeng Zhang, Xiaogang Wang, Hongsheng Li
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 recurrent correspondence-based pose optimization with differentiable LM | RNNPose · LINEMOD | ADD(-S) accuracy: 97.37 vs 96.1 | Improved |
| Use recurrent correspondence-based pose optimization with descriptor weighting | RNNPose · Occlusion LINEMOD | ADD(-S) accuracy: 51.6 -> 60.65 | Improved |
| Use RNNPose refinement after PoseCNN initialization | YCB-Video · YCB-Video | AUC, ADD(-S): 61.3 -> 83.1 | Improved |
| Add correspondence-field supervision (ablation) | RNNPose · LINEMOD | ADD(-S) accuracy at 0.02d: 21.85 -> 50.39 | Improved |
| Add model alignment loss and end-to-end pose supervision (ablation) | RNNPose · LINEMOD | ADD(-S) accuracy at 0.02d: 33.72 -> 50.39 | Improved |
| Add rigid-pose correspondence-field rectification (ablation) | RNNPose · LINEMOD | ADD(-S) accuracy at 0.02d: 44.68 -> 50.39 | Improved |
| Add 3D context features instead of omitting context (ablation) | RNNPose · LINEMOD | ADD(-S) accuracy at 0.02d: 44.82 -> 50.39 | Improved |
| Use 3D context features instead of 2D context features (ablation) | RNNPose · LINEMOD | ADD(-S) accuracy at 0.02d: 47.44 -> 50.39 | Improved |
| Add descriptor-based similarity score weighting for unreliable correspondences (ablation) | RNNPose · Occlusion LINEMOD | ADD(-S) accuracy at 0.05d: 27.21 -> 31.15 | Improved |
Later papers that compared with this method
1 later accepted paper reports RNNPose as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Shape-Constraint Recurrent Flow for 6D Object Pose Estimation (CVPR 2023 · 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 3 of 3 on most shared results.
- RePOSE — RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering (ICCV 2021) · better on 3 of 3 shared results
- GDR-Net — GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation (CVPR 2021) · better on 1 of 1 shared result
- DPOD — DPOD: 6D Pose Object Detector and Refiner (ICCV 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
- PORF: POSE RESIDUAL FIELD FOR ACCURATE NEURAL SURFACE RECONSTRUCTION (ICLR 2024 · similarity 0.87)
- Co-op: Correspondence-based Novel Object Pose Estimation (CVPR 2025 · similarity 0.87)
- SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow (CVPR 2025 · similarity 0.86)
- RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects (CVPR 2025 · similarity 0.86)
- GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement (CVPR 2024 · similarity 0.86)
- Neural Refinement for Absolute Pose Regression with Feature Synthesis (CVPR 2024 · similarity 0.86)
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.
