Research map / Point clouds / Point cloud classification
S3E: Self-Supervised State Estimation for Radar-Inertial System
Shengpeng Wang, Yulong Xie, Qing Liao, 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 rotation-based cross fusion (ablation) | S3E · ColoRadar | Chamfer distance (m): 0.16 -> 0.14 | Improved |
| add rotation-based cross fusion (ablation) | S3E · ColoRadar | Hausdorff distance (m): 0.62 -> 0.55 | Improved |
| add rotation-based cross fusion (ablation) | S3E · ColoRadar | translation error (%): 3.23 -> 2.84 | Improved |
| add rotation-based cross fusion (ablation) | S3E · ColoRadar | rotation error (deg/100m): 2.57 -> 2.15 | Improved |
| use self-supervised S3E instead of supervised Milliego | S3E · ColoRadar longboard | translation error (%): 9.14 -> 5.69 | Improved |
| use S3E instead of Milliego | S3E · ColoRadar outdoors | rotation error (deg/100m): 5.92 -> 3.83 | Improved |
| use S3E instead of Milliego | S3E · ColoRadar arpg_lab | rotation error (deg/100m): 7.89 -> 4.28 | Improved |
| use S3E instead of Milliego | S3E · ColoRadar edgar_classroom | translation error (%): 2.32 -> 2.45 | Hurt |
| use S3E instead of Milliego | S3E · ColoRadar aspen_run | rotation error (deg/100m): 11.0 -> 11.3 | Hurt |
| use S3E instead of supervised Milliego (average) | S3E · ColoRadar average | rotation error (deg/100m): 16.8% | Improved |
| use S3E instead of Milliego on unseen scenes | S3E · Self-collected outdoor_seq0 | translation error (%): 14.3 -> 5.37 | Improved |
| use S3E instead of Milliego on unseen scenes | S3E · Self-collected indoor_seq0 | translation error (%): 9.84 -> 2.69 | Improved |
Closest papers by meaning
- Mitigating Radar-Inertial Calibration Ambiguities via SO(3) Manifold Steering (ECCV 2026 · similarity 0.86)
- RadarMOSEVE: A Spatial-Temporal Transformer Network for Radar-Only Moving Object Segmentation and Ego-Velocity Estimation (AAAI 2024 · similarity 0.81)
- NEAR: Neural Electromagnetic Array Response (ICML 2025 · similarity 0.81)
- 3D Point Splatting for mmWave Radar Novel View Synthesis (NeurIPS 2026 · similarity 0.80)
- TransLoc4D: Transformer-based 4D Radar Place Recognition (CVPR 2024 · similarity 0.80)
- HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection (AAAI 2025 · similarity 0.80)
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.
