Research map / 3D vision / Human pose estimation
DPOD: 6D Pose Object Detector and Refiner
Sergey Zakharov, Ivan Shugurov, Slobodan Ilic
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 deep refinement after DPOD | DPOD (synthetic) · LineMOD (trained on synthetic) | ADD accuracy (%): 50 -> 66.43 | Improved |
| add deep refinement after DPOD | DPOD (real) · LineMOD (trained on real) | ADD accuracy (%): 82.98 -> 95.15 | Improved |
| add deep refinement after DPOD | DPOD (real) · OCCLUSION | ADD accuracy (%): 32.79 -> 47.25 | Improved |
| use our refiner instead of DeepIM on DPOD poses | DPOD (real) · LineMOD | ADD accuracy (%): 91.81 -> 95.15 | Improved |
| use DPOD poses as initialization instead of PoseCNN for DeepIM | DeepIM · LineMOD | ADD accuracy (%): 88.6 -> 91.81 | Improved |
| increase RANSAC iterations from 5 to 150 (ablation) | DPOD (real) · LineMOD | ADD accuracy without refinement (%): 59.15 -> 82.98 | Improved |
| increase RANSAC iterations from 150 to 500 (ablation) | DPOD (real) · LineMOD | ADD accuracy without refinement (%): 82.98 -> 84.66 | No clear effect |
| increase RANSAC iterations from 150 to 500 (ablation) | DPOD + refiner (real) · LineMOD | ADD accuracy with refinement (%): 95.15 -> 95.39 | No clear effect |
| use 25 RANSAC iterations with refinement (ablation) | DPOD + refiner (real) · LineMOD | ADD accuracy with refinement (%): 92.59 | Improved |
| replace UV mapping with 3-channel UVW mapping (ablation) | DPOD · LineMOD and OCCLUSION | ADD accuracy | No clear effect |
| train on real data instead of synthetic data | DPOD · LineMOD | ADD accuracy (%): 50 -> 82.98 | Improved |
| classify discretized UV colors instead of directly regressing 3D coordinates (ablation) | DPOD correspondence head · LineMOD | correspondence quality | Improved |
Later papers that compared with this method
10 later accepted papers report DPOD as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.
- OSOP: A Multi-Stage One Shot Object Pose Estimation Framework (CVPR 2022 · better on 1 of 1 shared result)
- RNNPose: Recurrent 6-DoF Object Pose Refinement With Robust Correspondence Field Estimation and Pose Optimization (CVPR 2022 · better on 1 of 1 shared result)
- RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering (ICCV 2021 · better on 2 of 2 shared results)
- DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation (TPAMI 2021 · better on 2 of 2 shared results)
- GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation (CVPR 2021 · better on 0 of 1 shared result)
- Keypoint-Graph-Driven Learning Framework for Object Pose Estimation (CVPR 2021 · better on 1 of 1 shared result)
- PR-GCN: A Deep Graph Convolutional Network With Point Refinement for 6D Pose Estimation (ICCV 2021 · better on 1 of 1 shared result)
- Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation (TPAMI 2021 · better on 1 of 1 shared result)
2 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PVNet — PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation (CVPR 2019) · better on 2 of 3 shared results
- SSD6D — SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again (ICCV 2017) · better on 3 of 3 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
- DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation (TPAMI 2021 · similarity 0.94)
- Coupled Iterative Refinement for 6D Multi-Object Pose Estimation (CVPR 2022 · similarity 0.88)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.88)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · similarity 0.87)
- RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects (CVPR 2025 · similarity 0.87)
- MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images (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.
