csiro-robotics/LoGG3D-Net

[ICRA 2022] The official repository for "LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition", In 2022 International Conference on Robotics and Automation (ICRA), pp. 2215-2221.

42
/ 100
Emerging

This project helps autonomous robots and vehicles recognize previously visited locations in real-world environments using 3D sensor data. It takes in 3D point cloud scans from sensors like LiDAR and outputs a way for the robot to accurately identify if it has been to a specific place before, even if conditions have changed. This is ideal for robotics engineers and autonomous vehicle developers building navigation and mapping systems.

109 stars. No commits in the last 6 months.

Use this if you need robust 3D place recognition for robotic navigation, mapping, or localization in complex outdoor environments.

Not ideal if your application focuses on 2D vision, uses only image data, or requires precise 6-DoF metric localization without the need for global place recognition.

robotics-navigation autonomous-vehicles 3D-mapping localization LiDAR-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

109

Forks

18

Language

Python

License

Last pushed

Oct 06, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/csiro-robotics/LoGG3D-Net"

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