Research map / Detection and segmentation / 3D detection and driving
Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 Radar-to-LiDAR fusion to CenterPoint (ablation) | CenterPoint · nuScenes val | mAP: 59.3 -> 60.4 (+1.1) | Helped |
| Add Radar-to-LiDAR fusion to CenterPoint (ablation) | CenterPoint · nuScenes val | mAVE: 30.3 -> 26.2 (-4.1) | Helped |
| Add query-based LiDAR-to-Radar height feature fusion (QHF) (ablation) | R2L fusion only · nuScenes val | mAP: 60.4 -> 61.3 (+2.0) | Helped |
| Add query-based LiDAR-to-Radar height feature fusion (QHF) (ablation) | R2L fusion only · nuScenes val | mAVE: 26.2 -> 25.1 (-5.2) | Helped |
| Add query-based LiDAR-to-Radar BEV feature fusion (QBF) (ablation) | R2L fusion only · nuScenes val | mAP: 60.4 -> 61.9 (+2.6) | Helped |
| Add query-based LiDAR-to-Radar BEV feature fusion (QBF) (ablation) | R2L fusion only · nuScenes val | mAVE: 26.2 -> 25.5 (-4.8) | Helped |
| Add both QHF and QBF to R2L fusion (ablation) | CenterPoint · nuScenes val | mAP: 59.3 -> 62.0 (+2.7) | Helped |
| Add both QHF and QBF to R2L fusion (ablation) | CenterPoint · nuScenes val | mAVE: 30.3 -> 25.0 (-5.3) | Helped |
| Use bidirectional LiDAR-Radar fusion instead of the LiDAR-only baseline | CenterPoint · nuScenes test | mAP: 60.3 -> 63.1 | Helped |
| Use bidirectional LiDAR-Radar fusion instead of the LiDAR-only baseline | CenterPoint · nuScenes test | mAVE: 28.8 -> 25.7 | Helped |
| Use Bi-LRFusion rather than MVDet | ORR vehicle detection · ORR, IoU=0.5 | AP: 90.9 -> 92.2 | Helped |
| Use Bi-LRFusion rather than MVDet | ORR vehicle detection · ORR, IoU=0.8 | AP: 74.6 -> 74.4 | Hurt |
Closest papers by meaning
- Towards Robust 3D Object Detection with LiDAR and 4D Radar Fusion in Various Weather Conditions (CVPR 2024 · similarity 0.88)
- RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features (CVPR 2024 · similarity 0.87)
- CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detection (NeurIPS 2024 · similarity 0.86)
- HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection (AAAI 2025 · similarity 0.86)
- RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection (ICLR 2025 · similarity 0.85)
- RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection (CVPR 2024 · similarity 0.85)
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.