vzyrianov/lidargen

Official implementation of "Learning to Generate Realistic LiDAR Point Clouds" (ECCV 2022)

38
/ 100
Emerging

This project helps researchers and developers in autonomous driving or robotics generate realistic LiDAR point clouds for simulation and testing. It takes existing LiDAR scan data (like from KITTI-360) and outputs new, synthetic LiDAR point cloud data, which can be used to augment datasets or test algorithms in varied scenarios. This tool is for those who need to create diverse and realistic LiDAR data without extensive real-world collection.

149 stars. No commits in the last 6 months.

Use this if you need to create synthetic, realistic LiDAR point clouds to expand your datasets for training and evaluating autonomous driving or robotics systems.

Not ideal if you primarily work with other sensor data types or require only raw LiDAR data without the need for generative modeling.

autonomous-driving robotics lidar-simulation sensor-data-generation computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

149

Forks

13

Language

Python

License

MIT

Last pushed

Sep 16, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/vzyrianov/lidargen"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.