Research map / 3D vision / Human pose estimation
Ultra-Precision 6DoF Pose Estimation Using 2-D Interpolated Discrete Fourier Transform
Guowei Shi, Zian Mao, Peisen Huang
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 2D-IpDFT instead of QSE | pose estimation · computation time 640x480 | time (ms): 296 -> 12.4 | Improved |
| use 2D-IpDFT instead of zero-padding 8x | pose estimation · computation time 1600x1200 | time (ms): 2059 -> 77.5 | Improved |
| use 2D-IpDFT instead of QSE | single-axis motion · tx RMSE (nm) | RMSE: 236 -> 21 | Improved |
| use 2D-IpDFT instead of linear regression | single-axis motion · tz RMSE (nm) | RMSE: 30906 -> 244 | Improved |
| use 2D-IpDFT instead of QSE | ICCV trajectory · ty RMSE (nm) | RMSE: 465 -> 7 | Improved |
| use 2D-IpDFT instead of QSE | helical trajectory · tz RMSE (nm) | RMSE: 16037 -> 1664 | Improved |
| increase exposure time from 10 to 30 ms for 2D-IpDFT (ablation) | 2D-IpDFT · circular trajectory | RMSE (nm): 38 -> 35 | Improved |
| increase exposure time from 10 to 30 ms for QSE (ablation) | QSE · circular trajectory | RMSE (nm): 182 -> 185 | Hurt |
| increase pattern periods from 6.4 to 32 for 2D-IpDFT (ablation) | 2D-IpDFT · circular trajectory | RMSE (nm): 57 -> 8 | Improved |
| increase pattern periods from 6.4 to 32 for linear regression (ablation) | linear regression · circular trajectory | RMSE (nm): 20895 -> 17 | Improved |
| go from light to heavy defocus blur for 2D-IpDFT (ablation) | 2D-IpDFT · circular trajectory | RMSE (nm): 197 -> 348 | Hurt |
| go from light to heavy blur for linear regression (ablation) | linear regression · circular trajectory | RMSE (nm): 342 -> 5668 | Hurt |
Closest papers by meaning
- Towards Co-Evaluation of Cameras HDR and Algorithms for Industrial-Grade 6DoF Pose Estimation (CVPR 2024 · similarity 0.84)
- iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting (CVPR 2025 · similarity 0.84)
- FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation (CVPR 2024 · similarity 0.84)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.82)
- Any6D: Model-free 6D Pose Estimation of Novel Objects (CVPR 2025 · similarity 0.82)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · similarity 0.81)
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.
