Research map / Detection and segmentation / 3D detection and driving
Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving
Check 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 |
|---|---|---|---|
| Use Pyramid rather than Center placement | PV-RCNN · CARLA Car 3D | AP_R40@0.70: 52.15 -> 57.44 | Helped |
| Use Trapezoid rather than Center placement | PV-RCNN · CARLA Van and Cyclist 3D | AP_R40@0.50: 40.09 -> 42.85 | Helped |
| Roll the side LiDARs in Line placement (ablation) | PV-RCNN · CARLA Car 3D | AP: 55.50 -> 54.53 | Hurt |
| Roll the side LiDARs in Line placement (ablation) | PV-RCNN · CARLA Car BEV | AP: 65.42 -> 63.17 | Hurt |
| Roll the side LiDARs in Line placement (ablation) | PointRCNN · CARLA Car 3D | AP: 48.25 -> 45.12 | Hurt |
| Roll the side LiDARs in Pyramid placement (ablation) | PV-RCNN · CARLA Car 3D | AP: 57.44 -> 53.91 | Hurt |
| Roll the side LiDARs in Pyramid placement (ablation) | PointRCNN · CARLA Car BEV | AP: 56.97 -> 50.74 | Hurt |
| Pitch the front LiDAR in Pyramid placement (ablation) | PV-RCNN · CARLA Car 3D | AP: 57.44 -> 53.46 | Hurt |
| Pitch the front LiDAR in Pyramid placement (ablation) | PointRCNN · CARLA Car BEV | AP: 56.97 -> 51.39 | Hurt |
| Increase surrounding car density from Sparse to Dense (ablation) | PV-RCNN with Square placement · CARLA Car 3D | AP: 54.48 -> 57.98 | Helped |
| Increase surrounding car density from Sparse to Dense (ablation) | Square placement · CARLA Car scenes | IG (10^3): 410.70 -> 607.072 | Helped |
Closest papers by meaning
- Is Your LiDAR Placement Optimized for 3D Scene Understanding? (NeurIPS 2024 · similarity 0.92)
- Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving (CVPR 2019 · similarity 0.89)
- Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving (ICLR 2020 · similarity 0.88)
- ALSO: Automotive Lidar Self-Supervision by Occupancy Estimation (CVPR 2023 · similarity 0.88)
- An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains (CVPR 2024 · similarity 0.88)
- JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data (CVPR 2025 · similarity 0.87)
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.