Research map / Point clouds / Point cloud classification
DNOI-4DRO: Deep 4D Radar Odometry with Differentiable Neural-Optimization Iterations
Shouyi Lu, Huanyu Zhou, Guirong Zhuo, Xiao Tang
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 multi-scale geometric feature branch (ablation) | DNOI-4DRO · VoD | mean translational RMSE (m/m): 0.030 -> 0.024 | Improved |
| add clustering-based class-aware feature branch (ablation) | DNOI-4DRO · VoD | mean translational RMSE (m/m): 0.030 -> 0.024 | Improved |
| add global transformer (ablation) | DNOI-4DRO · VoD | mean translational RMSE (m/m): 0.027 -> 0.024 | Improved |
| add AMBA geometric optimization layer (ablation) | DNOI-4DRO · VoD | mean rotational RMSE (deg/m): 0.089 -> 0.029 | Improved |
| add differentiable iteration operator instead of direct pose regression (ablation) | DNOI-4DRO · VoD | mean translational RMSE (m/m): 0.348 -> 0.024 | Improved |
| add per-point confidence weights (ablation) | DNOI-4DRO · VoD | mean translational RMSE (m/m): 0.060 -> 0.024 | Improved |
| use directional (fine-grained) confidence instead of one scalar per point (ablation) | DNOI-4DRO · VoD | mean translational RMSE (m/m): 0.049 -> 0.024 | Improved |
| use DNOI-4DRO instead of previous best learning-based radar odometry | DNOI-4DRO · VoD | mean translational/rotational RMSE: 0.071 -> 0.023 (trans); 0.051 -> 0.027 (rot) | Improved |
| use radar-only DNOI-4DRO versus LiDAR Full A-LOAM | DNOI-4DRO · VoD | mean translational RMSE (m/m): 0.034 (A-LOAM) vs 0.023 trans; 0.084 vs 0.027 rot | Mixed |
| use DNOI-4DRO versus 4DRadarSLAM on long trajectories | DNOI-4DRO · Snail-Radar | mean translational RMSE (%): 13.39 -> 4.60 | Improved |
Closest papers by meaning
- TransLoc4D: Transformer-based 4D Radar Place Recognition (CVPR 2024 · similarity 0.86)
- RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar (NeurIPS 2024 · similarity 0.84)
- SCKD: Semi-Supervised Cross-Modality Knowledge Distillation for 4D Radar Object Detection (AAAI 2025 · similarity 0.83)
- Towards Robust 3D Object Detection with LiDAR and 4D Radar Fusion in Various Weather Conditions (CVPR 2024 · similarity 0.83)
- DeepPointMap: Advancing LiDAR SLAM with Unified Neural Descriptors (AAAI 2024 · similarity 0.83)
- L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection (AAAI 2025 · similarity 0.82)
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.
