Research map / 3D vision / Human pose estimation
Implicit 3D Orientation Learning for 6D Object Detection from RGB Images
Martin Sundermeyer, Zoltan-Csaba Marton, Maximilian Durner, Manuel Brucker, Rudolph Triebel
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 random add-brightness augmentation to dynamic lighting (ablation) | AAE · T-LESS object 5 Primesense | AUC_vsd: 0.472 -> 0.611 | Improved |
| add contrast augmentation (ablation) | AAE · T-LESS object 5 Primesense | AUC_vsd: 0.611 -> 0.825 | Improved |
| add multiply augmentation (ablation) | AAE · T-LESS object 5 Primesense | AUC_vsd: 0.825 -> 0.876 | Improved |
| add color inversion augmentation (ablation) | AAE · T-LESS object 5 Primesense | AUC_vsd: 0.876 -> 0.877 | No clear effect |
| add dynamic lighting (to add, contrast, multiply) (ablation) | AAE · T-LESS object 5 Primesense | AUC_vsd: 0.861 -> 0.876 | Improved |
| add contrast augmentation (ablation) | AAE · T-LESS object 5 Kinect | AUC_vsd: 0.580 -> 0.701 | Improved |
| add multiply augmentation (ablation) | AAE · T-LESS object 5 Kinect | AUC_vsd: 0.701 -> 0.855 | Improved |
| add color inversion augmentation (ablation) | AAE · T-LESS object 5 Kinect | AUC_vsd: 0.855 -> 0.897 | Improved |
| add dynamic lighting (to add, contrast, multiply, invert) (ablation) | AAE · T-LESS object 5 Kinect | AUC_vsd: 0.903 -> 0.897 | Hurt |
| add perspective correction (ablation) | AAE RetinaNet · T-LESS | recall (%): 18.35 -> 19.26 (+0.91) | Improved |
| train on untextured CAD models instead of 3D reconstructions (ablation) | AAE RetinaNet · T-LESS | recall (%): 19.26 -> 26.79 | Improved |
| add depth-based ICP refinement (ablation) | AAE RetinaNet · T-LESS | recall (%): 19.26 -> 68.57 | Improved |
Closest papers by meaning
- Augmented Autoencoders: Implicit 3D Orientation Learning for 6D Object Detection (IJCV 2019 · similarity 0.99)
- Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation (ECCV 2016 · similarity 0.89)
- FS-Net: Fast Shape-Based Network for Category-Level 6D Object Pose Estimation With Decoupled Rotation Mechanism (CVPR 2021 · similarity 0.88)
- Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes (ICCV 2025 · similarity 0.88)
- Pose without Guesses: Generalizable Object Pose Estimation From a Single Reference (IJCV 2026 · similarity 0.88)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (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.
