Research map / Detection and segmentation / 3D detection and driving
MMVR: Millimeter-wave Multi-View Radar Dataset and Benchmark for Indoor Perception
Mohammad Mahbubur Rahman, Ryoma Yataka, Sorachi Kato, Pu Wang, Peizhao Li, Adriano Cardace, Petros Boufounos
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 |
|---|---|---|---|
| use 12 radar frames instead of 4 (ablation) | RFMask · MMVR P1 S1 object detection | AP: 25.53 -> 33.12 | Improved |
| use 18 frames instead of 12 (ablation) | RFMask · MMVR P1 S1 object detection | AP: 33.12 -> 32.78 | No clear effect |
| use 12 frames instead of 4 (ablation) | RF-Pose · MMVR P1 S1 pose estimation | AP: 46.24 -> 46.86 | No clear effect |
| add vertical radar view to horizontal view (ablation) | RF-Pose · MMVR P1 S1 pose estimation | AP: 22.22 -> 46.24 | Improved |
| add vertical radar view to horizontal view (ablation) | RFMask · MMVR P1 S1 object detection | AP: 24.64 -> 25.53 | Improved |
| replace RFMask with DETR backbone (ablation) | radar object detection · MMVR P1 S1 (single view) | AP: 24.64 -> 35.78 | Improved |
| evaluate on unseen cluttered room (S2) instead of random split (S1) | RFMask · MMVR P2 object detection | AP50: 61.50 -> 22.77 | Hurt |
| evaluate on unseen cluttered room (S2) instead of random split (S1) | RF-Pose · MMVR P2 pose estimation | AP50: 44.22 -> 11.98 | Hurt |
| evaluate on cluttered multi-subject P2 instead of open-foreground P1 | RFMask · MMVR S1 instance segmentation | IoU: 71.98 -> 65.30 | Hurt |
Closest papers by meaning
- RETR: Multi-View Radar Detection Transformer for Indoor Perception (NeurIPS 2024 · similarity 0.87)
- V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception (NeurIPS 2025 · similarity 0.87)
- MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception (NeurIPS 2026 · similarity 0.86)
- RadarMOSEVE: A Spatial-Temporal Transformer Network for Radar-Only Moving Object Segmentation and Ego-Velocity Estimation (AAAI 2024 · similarity 0.86)
- MVDoppler-Pose: Multi-Modal Multi-View mmWave Sensing for Long-Distance Self-Occluded Human Walking Pose Estimation (CVPR 2025 · similarity 0.84)
- RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar (NeurIPS 2024 · similarity 0.84)
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.
