Research map / Point clouds / Point cloud classification
Optimizing the Placement of Roadside LiDARs for Autonomous Driving
Wentao Jiang, Hao Xiang, Xinyu Cai, Runsheng Xu, Jiaqi Ma, Yikang Li, Gim Hee Lee, Si Liu
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 perceptual-gain greedy placement instead of random placement | roadside LiDAR placement · Roadside-Opt, intermediate fusion, M=2 | AP@0.5: 0.44 -> 0.63 | Improved |
| use greedy placement instead of random on late fusion | roadside LiDAR placement · Roadside-Opt, late fusion, M=2 | AP@0.5: 0.31 -> 0.56 | Improved |
| use greedy method instead of brute-force search | roadside LiDAR placement, M=2 · Roadside-Opt | AP@0.5 early fusion: 0.82 -> 0.78 | No clear effect |
| use greedy method instead of brute force | runtime · Roadside-Opt | computation time: 11 hours -> within 10 seconds (M=2) | Improved |
| add more LiDARs sequentially (ablation) | greedy placement · Roadside-Opt, intermediate fusion | AP@0.7: 0.17 -> 0.76 (M=1 to 5) | Improved |
| add smoothing loss to the perception predictor (ablation) | perception predictor · Roadside-Opt | perception ability map quality (qualitative) | Improved |
Closest papers by meaning
- Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving (CVPR 2022 · similarity 0.89)
- Is Your LiDAR Placement Optimized for 3D Scene Understanding? (NeurIPS 2024 · similarity 0.89)
- RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception (ECCV 2026 · similarity 0.88)
- LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes (CVPR 2024 · similarity 0.85)
- JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data (CVPR 2025 · similarity 0.84)
- StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models (CVPR 2025 · 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.
