worldbench/LiDARCrafter

[AAAI 2026 Oral] LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences

42
/ 100
Emerging

This project helps self-driving car engineers and researchers create realistic, dynamic 4D LiDAR data for virtual testing environments. By inputting descriptions or existing 3D layouts, it generates detailed LiDAR point cloud sequences that simulate real-world driving scenarios. The output is a highly controllable and spatiotemporally consistent simulation of a dynamic environment, useful for training and validating autonomous vehicle systems.

188 stars.

Use this if you need to generate diverse and controllable 4D LiDAR sequences to rigorously test autonomous driving algorithms in simulated environments.

Not ideal if you are looking for a tool to process static 3D LiDAR scans or perform object detection directly on real-world LiDAR data.

autonomous-driving LiDAR-simulation sensor-data-generation virtual-testing robotics-research
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 11 / 25

How are scores calculated?

Stars

188

Forks

13

Language

Python

License

MIT

Last pushed

Dec 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/worldbench/LiDARCrafter"

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