Research map / Detection and segmentation / 3D detection and driving
Radatron: Accurate Detection Using Multi-Resolution Cascaded MIMO Radar
Sohrab Madani, Jayden Guan, Waleed Ahmed, Saurabh Gupta, Haitham Hassanieh
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 motion compensation algorithm (ablation) | Radatron multi-res · Radatron test set (overall) | AP75: 46.9 -> 56.3 | Improved |
| add motion compensation algorithm (ablation) | Radatron multi-res · Radatron test set (overall) | AP50: 91.1 -> 92.6 | Improved |
| add low-resolution branch (multi-res fusion) (ablation) | Radatron high-res only · Radatron test set (incoming cars) | AP50: 73.1 -> 79.7 | Improved |
| add low-resolution branch (multi-res fusion) (ablation) | Radatron high-res only · Radatron test set (incoming cars) | AP75: 34.6 -> 38.2 | Improved |
| add low-resolution branch (multi-res fusion) (ablation) | Radatron high-res only · Radatron test set (oriented cars) | AP50: 90.7 -> 88.7 | Hurt |
| use high-resolution cascaded radar instead of prior-work radar | Radatron · Radatron test set (overall) | AP75: 40.4 -> 56.3 | Improved |
| use high-resolution cascaded radar instead of prior-work radar | Radatron · Radatron test set (oriented cars) | AP75: 24.0 -> 57.1 | Improved |
| use multi-res fusion with compensation instead of single-TX | Radatron · Radatron test set (oriented cars) | AP75: 31.6 -> 57.1 | Improved |
| add motion compensation and fusion instead of stand-alone cascaded | Radatron · Radatron test set (incoming cars) | AP50: 65.9 -> 79.7 | Improved |
| add our motion compensation | MVDNet · Radatron test set (incoming cars) | AP50: 3.7 -> 41.9 | Improved |
| add our motion compensation | MVDNet · Radatron test set (straight cars) | AP50: 62.5 -> 90.5 | Improved |
| use Radatron high-res network instead of compensated MVDNet | MVDNet w/ compensation · Radatron test set (incoming cars) | AP50: 41.9 -> 73.1 | Improved |
Closest papers by meaning
- RadSimReal: Bridging the Gap Between Synthetic and Real Data in Radar Object Detection With Simulation (CVPR 2024 · similarity 0.82)
- HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection (AAAI 2025 · similarity 0.82)
- NEAR: Neural Electromagnetic Array Response (ICML 2025 · similarity 0.81)
- V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception (NeurIPS 2025 · similarity 0.81)
- RadarMOSEVE: A Spatial-Temporal Transformer Network for Radar-Only Moving Object Segmentation and Ego-Velocity Estimation (AAAI 2024 · similarity 0.81)
- MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception (NeurIPS 2026 · 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.
