Research map / 3D vision / Human pose estimation
XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexity
Junwen Huang, Jiaqi Hu, Peter Yu, Slobodan Ilic, Martin Sundermeyer, Benjamin Busam
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 |
|---|---|---|---|
| evaluate unseen-object SAM6D on XYZ-IBD instead of BOP-Core 5 | SAM6D · 6D detection | AP: 0.704 -> 0.578 | Hurt |
| evaluate seen-object GDRN on XYZ-IBD instead of BOP-Core 5 | GDRN · 6D detection | AP: 0.827 -> 0.266 | Hurt |
| evaluate YOLOX on XYZ-IBD instead of BOP-Core 5 | YOLOX · 2D detection | AP: 0.798 -> 0.774 | Hurt |
| evaluate NIDS-Net on XYZ-IBD instead of BOP-Core 5 | NIDS-Net · 2D detection unseen | AP: 0.494 -> 0.258 | Hurt |
| evaluate CNOS(SAM) on XYZ-IBD instead of BOP-Core 5 | CNOS(SAM) · 2D detection unseen | AP: 0.361 -> 0.275 | Hurt |
| use unseen-object methods instead of seen-object methods on XYZ-IBD 6D detection | 6D detection · XYZ-IBD | AP: 0.266 -> 0.578 | Improved |
| increase Gaussian depth noise sigma from 0.0 to 0.26 mm (ablation) | calibration simulation · viewpoint calibration | RMSE (mm): 0.199 -> 0.248 | Hurt |
Closest papers by meaning
- Towards Co-Evaluation of Cameras HDR and Algorithms for Industrial-Grade 6DoF Pose Estimation (CVPR 2024 · similarity 0.86)
- HouseCat6D - A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios (CVPR 2024 · similarity 0.85)
- RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges (CVPR 2025 · similarity 0.85)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.85)
- UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References (CVPR 2025 · similarity 0.84)
- 6D Object Pose Tracking in Internet Videos for Robotic Manipulation (ICLR 2025 · similarity 0.84)
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.
