Short reads from the team building SiRLab: how we simulate weather, benchmark co-simulation, and keep point-level labels precise.
Real-time synthetic LiDAR aligned to RGB and labels (stencil IDs), with GPU-resident reconstruction from render passes for dataset-scale throughput and closed-loop simulation.
A single place to browse our current preview datasets and open them in the browser-based LiDAR viewer.
A technical summary of how we drive weather effects from the simulation so every sensor sees the same state.
A taxonomy-first label registry that assigns stable IDs (and palettes) so RGB, segmentation, and LiDAR agree across builds, scenes, and clients.
Real-time synthetic LiDAR aligned to RGB and labels (stencil IDs), with GPU-resident reconstruction from render passes for dataset-scale throughput and closed-loop simulation.
A single place to browse our current preview datasets and open them in the browser-based LiDAR viewer.
A technical summary of how we drive weather effects from the simulation so every sensor sees the same state.
A taxonomy-first label registry that assigns stable IDs (and palettes) so RGB, segmentation, and LiDAR agree across builds, scenes, and clients.
