Research map / Image generation / Image restoration
Through Fog High-Resolution Imaging Using Millimeter Wave Radar
Junfeng Guan, Sohrab Madani, Suraj Jog, Saurabh Gupta, Haitham Hassanieh
Check 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 HawkEye instead of raw mmWave radar heatmaps | mmWave car imaging · Clean Air | ranging error: 53 cm -> 30 cm | Improved |
| Use HawkEye instead of raw mmWave radar heatmaps | mmWave car imaging · Fog | ranging error: 67 cm -> 50 cm | Improved |
| Use HawkEye instead of raw mmWave radar heatmaps | mmWave car imaging · Clean Air | length error: 179 cm -> 47 cm | Improved |
| Use HawkEye instead of raw mmWave radar heatmaps | mmWave car imaging · Fog | length error: 222 cm -> 83 cm | Improved |
| Use HawkEye instead of raw mmWave radar heatmaps | mmWave car imaging · Clean Air | orientation error: 64◦ -> 27◦ | Improved |
| Use HawkEye instead of raw mmWave radar heatmaps | mmWave car imaging · Fog | orientation error: 72◦ -> 29◦ | Improved |
| Use HawkEye instead of raw mmWave radar heatmaps | mmWave car imaging · Clean Air | fictitious reflections: 15.6% -> 1.5% | Improved |
| Use HawkEye instead of raw mmWave radar heatmaps | mmWave car imaging · Fog | fictitious reflections: 20.9% -> 2.5% | Improved |
| Add the conditional GAN and discriminator rather than train with L1-based losses alone | HawkEye car imaging · Clean Air | length error: 97 cm -> 47 cm | Improved |
| Add the conditional GAN and discriminator rather than train with L1-based losses alone | HawkEye car imaging · Clean Air | ranging error: 40 cm -> 30 cm | Hurt |
| Add the conditional GAN and discriminator rather than train with L1-based losses alone | HawkEye car imaging · Fog | orientation error: 38◦ -> 29◦ | Improved |
| Add the conditional GAN and discriminator rather than train with L1-based losses alone | HawkEye car imaging · Synthesized Data | ranging error: 20 cm -> 23 cm | Hurt |
Closest papers by meaning
- CoIR: Compressive Implicit Radar (TPAMI 2023 · similarity 0.88)
- mmIR: Frequency-Space Inverse Rendering for 3D Millimeter-Wave Radar ADC Synthesis (ECCV 2026 · similarity 0.87)
- 3D Point Splatting for mmWave Radar Novel View Synthesis (NeurIPS 2026 · similarity 0.83)
- MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception (NeurIPS 2026 · similarity 0.83)
- RadarMOSEVE: A Spatial-Temporal Transformer Network for Radar-Only Moving Object Segmentation and Ego-Velocity Estimation (AAAI 2024 · similarity 0.81)
- MVDoppler-Pose: Multi-Modal Multi-View mmWave Sensing for Long-Distance Self-Occluded Human Walking Pose Estimation (CVPR 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.
