QingyongHu/SQN

SQN in Tensorflow (ECCV'2022)

40
/ 100
Emerging

This project helps urban planners, architects, or autonomous vehicle developers automatically identify objects and features within large-scale 3D environment scans. You provide a raw 3D point cloud dataset, and it outputs a segmented point cloud where different types of objects (like buildings, roads, trees, or vehicles) are clearly labeled. This is particularly useful for professionals working with LiDAR or photogrammetry data who need to understand the composition of a 3D space.

117 stars. No commits in the last 6 months.

Use this if you need to semantically categorize parts of large 3D point clouds, especially when you have limited annotated data.

Not ideal if your primary need is 3D object detection or instance segmentation of individual objects rather than overall scene understanding.

3D-mapping urban-planning autonomous-navigation LiDAR-processing spatial-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

117

Forks

13

Language

Python

License

MIT

Last pushed

Apr 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/QingyongHu/SQN"

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