Research map / 3D vision / Human pose estimation
Markerless Camera-to-Robot Pose Estimation via Self-Supervised Sim-to-Real Transfer
Jingpei Lu, Florian Richter, Michael C. Yip
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 CtRNet instead of DREAM or RoboPose | Camera-to-robot pose estimation · DREAM-real All | AUC ADD: 85.962 vs 56.988 for DREAM-Q; 85.962 vs 80.094 for RoboPose | Improved |
| Use CtRNet instead of Diff. Rendering | Camera-to-robot pose estimation · Baxter | PCK AUC: 93.94 vs 78.60 | Improved |
| Use CtRNet instead of Diff. Rendering | Camera-to-robot pose estimation · Baxter | ADD AUC: 83.93 vs 81.15 | Improved |
| Use CtRNet instead of DREAM | Baxter visual servoing · Baxter visual servoing | Trans. Err. (m): 0.235 ± 0.313 -> 0.002 ± 0.001 | Improved |
| Increase synthetic pretraining samples from 500 to 1000 (ablation) | CtRNet · Baxter | AUC ADD: 47.62 -> 76.65 | Improved |
| Increase synthetic pretraining samples from 1000 to 2000 (ablation) | CtRNet · Baxter | AUC ADD: 76.65 -> 82.98 | Improved |
| Increase synthetic pretraining samples beyond 2000 (ablation) | CtRNet · Baxter | AUC ADD: 82.98 -> 84.12 -> 83.93 | Mixed |
| Add segmentation loss L_seg (ablation) | CtRNet with 500 pretraining samples · Baxter | AUC ADD: 65.26 -> 47.62 | Hurt |
| Add segmentation loss L_seg (ablation) | CtRNet with 1000 pretraining samples · Baxter | AUC ADD: 69.71 -> 76.65 | Improved |
| Add segmentation loss L_seg (ablation) | CtRNet with 2000 pretraining samples · Baxter | AUC ADD: 76.20 -> 82.98 | Improved |
| Add segmentation loss L_seg (ablation) | CtRNet with 4000 pretraining samples · Baxter | AUC ADD: 78.71 -> 84.12 | Improved |
| Add segmentation loss L_seg (ablation) | CtRNet with 8000 pretraining samples · Baxter | AUC ADD: 79.07 -> 83.93 | Improved |
Closest papers by meaning
- Robot Structure Prior Guided Temporal Attention for Camera-to-Robot Pose Estimation From Image Sequence (CVPR 2023 · similarity 0.88)
- LA-Pose: Latent Action Pretraining Meets Pose Estimation (CVPR 2026 · similarity 0.87)
- Sim-to-Real 6D Object Pose Estimation via Iterative Self-Training for Robotic Bin Picking (ECCV 2022 · similarity 0.86)
- Real-time Holistic Robot Pose Estimation with Unknown States (ECCV 2024 · similarity 0.86)
- CRAVES: Controlling Robotic Arm With a Vision-Based Economic System (CVPR 2019 · similarity 0.86)
- GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking (NeurIPS 2026 · similarity 0.85)
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.
