Research map / 3D vision / Depth and stereo
Mitigating Radar-Inertial Calibration Ambiguities via SO(3) Manifold Steering
Chunshen Li, Shengpeng Wang, Zitao Ye, Wei Wang
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 temporal synthetic aperture rotation constraint (ablation) | RadarCalib · real-world dataset | mean rotation error (deg): 0.929 -> 0.254 | Improved |
| add temporal synthetic aperture rotation constraint (ablation) | RadarCalib · real-world dataset | mean translation error (cm): 0.661 -> 0.173 | Improved |
| add velocity consistency constraint (ablation) | RadarCalib · real-world dataset | mean translation error (cm): 0.421 -> 0.173 | Improved |
| add velocity consistency constraint (ablation) | RadarCalib · real-world dataset | mean rotation error (deg): 0.435 -> 0.254 | Improved |
| add pose consistency constraint (ablation) | RadarCalib · real-world dataset | mean translation error (cm): 0.852 -> 0.173 | Improved |
| add pose consistency constraint (ablation) | RadarCalib · real-world dataset | mean rotation error (deg): 0.491 -> 0.254 | Improved |
| use RadarCalib instead of iKalibr for calibration | Radar-IMU SLAM · Radar-IMU SLAM, Lab | ATE RMSE (m): 0.18 -> 0.12 | Improved |
| use RadarCalib instead of iKalibr for calibration | Radar-IMU SLAM · Radar-IMU SLAM, Outdoor | ATE RMSE (m): 0.28 -> 0.20 | Improved |
| use RadarCalib instead of iKalibr | calibration solver · optimization cost | total time (s): 48.00 -> 20.25 | Improved |
| use RadarCalib instead of iKalibr | calibration · Lab placement P.1 | roll rotation error (deg): 0.61 -> 0.11 | Improved |
| use TSA-enhanced heatmaps instead of CFAR detection | point cloud extraction · point cloud fidelity | Chamfer distance (m): 1.16-1.35 -> 0.93-1.10 | Improved |
| use TSA-enhanced heatmaps instead of CFAR detection | point cloud extraction · point cloud fidelity | Valid Point Ratio: 0.61-0.68 -> 0.70-0.71 | Improved |
Closest papers by meaning
- 3D Point Splatting for mmWave Radar Novel View Synthesis (NeurIPS 2026 · similarity 0.84)
- RC-AutoCalib: An End-to-End Radar-Camera Automatic Calibration Network (CVPR 2025 · similarity 0.82)
- DART: Implicit Doppler Tomography for Radar Novel View Synthesis (CVPR 2024 · similarity 0.82)
- Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation (NeurIPS 2026 · similarity 0.81)
- RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar (NeurIPS 2024 · similarity 0.81)
- RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark (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.
