Benchmark RadarAI BENCHMARK PROFILE
MR-LiDAR
MR-LiDAR is a multi-resolution LiDAR benchmark for roadside perception. It includes point cloud data and annotations from 16-, 32-, 80-, and 128-beam LiDARs in identical scenarios, covering vehicles and vulnerable road users at various distances.
- Released
- 2026-05-23
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
The benchmark targets the need for empirical comparison of LiDAR configurations to guide sensor selection in roadside perception systems, addressing cost and performance trade-offs.
Motivation
LiDAR model selection is a critical issue in roadside sensing systems, as it directly determines both perception capability and deployment cost.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.