HKUST-Aerial-Robotics/SG-Reg

[T-RO 2025] SG-Reg: Generalizable and Efficient Scene Graph Registration

27
/ 100
Experimental

This project helps autonomous robots or agents accurately find their position within a known map, or align their own map with another agent's map. It takes detailed environmental scans (RGB-D sequences) and processes them into 'scene graphs' to output precise positional alignments and matched features. This is ideal for robotics engineers, researchers, or operations engineers deploying autonomous systems in complex indoor environments.

134 stars. No commits in the last 6 months.

Use this if you need to precisely register two different semantic scene graphs from real-world indoor environments to enable tasks like multi-robot coordination or localization against a prior map.

Not ideal if you are working with outdoor environments, lack RGB-D sensor data, or do not need semantic scene graph representations for localization.

robotics autonomous-navigation slam scene-understanding multi-agent-systems
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

134

Forks

5

Language

Python

License

Last pushed

Jul 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/HKUST-Aerial-Robotics/SG-Reg"

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