hancyran/LiDAR-Diffusion

[CVPR 2024] Official implementation of "Towards Realistic Scene Generation with LiDAR Diffusion Models"

38
/ 100
Emerging

This project helps robotics engineers and autonomous vehicle developers create realistic, synthetic LiDAR scan data. It takes existing LiDAR point cloud data and generates new, diverse, and high-quality LiDAR scans that mimic real-world scenarios. This is useful for expanding datasets for training and testing autonomous systems without needing to collect more physical data.

279 stars. No commits in the last 6 months.

Use this if you need to generate highly realistic, synthetic 3D LiDAR point clouds to augment your training datasets for autonomous vehicles or robotics, especially when real-world data collection is costly or limited.

Not ideal if you are looking to process or analyze existing LiDAR data for tasks like object detection or mapping, rather than generating new synthetic data.

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

How are scores calculated?

Stars

279

Forks

18

Language

Python

License

MIT

Last pushed

May 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/hancyran/LiDAR-Diffusion"

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