astra-vision/LiDPM

[IV 2025, Oral] Official code of "LiDPM: Rethinking Point Diffusion for Lidar Scene Completion"

34
/ 100
Emerging

This project helps self-driving car engineers and robotics researchers complete partial LiDAR sensor scans, which often have gaps due to obstructions or sensor limitations. It takes in incomplete LiDAR point cloud data from real-world driving or robotics scenarios and outputs a densified, more complete representation of the environment. This is ideal for those working on autonomous navigation, perception, and environmental mapping.

No commits in the last 6 months.

Use this if you need to accurately fill in missing data points in LiDAR scans to create a more comprehensive and reliable 3D understanding of an environment for autonomous systems.

Not ideal if you are looking for a solution to process camera images or radar data, as this is specifically designed for LiDAR point cloud completion.

autonomous-driving robotics-perception lidar-processing 3d-mapping scene-completion
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 8 / 25

How are scores calculated?

Stars

82

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Aug 25, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/astra-vision/LiDPM"

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