Research map / 3D vision / Human pose estimation
SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again
Wadim Kehl, Fabian Manhardt, Federico Tombari, Slobodan Ilic, Nassir Navab
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 color-only SSD-style detector instead of RGB-D methods | SSD-6D · Tejani F1 | F1-score: 0.747 -> 0.885 | Improved |
| use RGB-only SSD-6D vs RGB-D baselines | SSD-6D · LineMOD per-object F1 | F1-score: ape 76.3 vs Kehl 98.1; benchvise 97.1 vs 94.8 | Mixed |
| small, textureless objects (ape, duck, cat) | SSD-6D · LineMOD per-object F1 | F1-score: ape 76.3; duck 80.0; cat 89.3 | Hurt |
| add depth-based (cloud) refinement over 2D refinement (ablation) | SSD-6D · Tejani pose (coffee) | VSS | Improved |
| add 2D edge-based refinement to unrefined poses (ablation) | SSD-6D · Tejani pose (coffee) | VSS | Improved |
| parse more views V in hypothesis pool (ablation) | SSD-6D · Tejani pose (coffee) | VSS | Improved |
| parse more in-plane rotations R in hypothesis pool (ablation) | SSD-6D · Tejani pose (coffee) | VSS | Improved |
| add depth refinement to RGB-only pose (ablation) | SSD-6D · LineMOD | ADD: 76.3% -> 90.9 % | Improved |
| RGB-only SSD-6D vs Brachmann trained on real images | SSD-6D · LineMOD RGB pose | ADD: 50.2% -> 76.3% | Improved |
| synthetic-only training vs Brachmann real-image training | SSD-6D · Multi-object dataset | AP: 0.51 -> 0.38 | Hurt |
Later papers that compared with this method
5 later accepted papers report SSD6D as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation (TPAMI 2021 · better on 1 of 1 shared result)
- PVNet: Pixel-Wise Voting Network for 6DoF Object Pose Estimation (TPAMI 2020 · better on 1 of 1 shared result)
- Explaining the Ambiguity of Object Detection and 6D Pose From Visual Data (ICCV 2019 · better on 9 of 10 shared results)
- DPOD: 6D Pose Object Detector and Refiner (ICCV 2019 · better on 3 of 3 shared results)
- Feature Mapping for Learning Fast and Accurate 3D Pose Inference From Synthetic Images (CVPR 2018 · 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
- Uni6D: A Unified CNN Framework Without Projection Breakdown for 6D Pose Estimation (CVPR 2022 · similarity 0.89)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · similarity 0.88)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.88)
- Any6D: Model-free 6D Pose Estimation of Novel Objects (CVPR 2025 · similarity 0.87)
- SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation (CVPR 2024 · 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.
