qinzheng93/GeoTransformer

[CVPR2022] Geometric Transformer for Fast and Robust Point Cloud Registration

46
/ 100
Emerging

This project helps you accurately align 3D scans or point clouds, even when they only partially overlap. You provide two point clouds, and it determines how to best rotate and translate one to match the other, producing a precisely registered single point cloud. This is ideal for professionals in robotics, autonomous vehicles, or 3D scanning who need to combine multiple sensor readings into a unified view.

923 stars. No commits in the last 6 months.

Use this if you need to robustly and quickly align 3D point clouds from different perspectives or sensors, especially in situations with low overlap between scans.

Not ideal if your primary need is object detection or classification within a single point cloud, rather than aligning two different point clouds.

3D scanning robotics autonomous vehicles computer vision spatial alignment
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

923

Forks

109

Language

Python

License

MIT

Last pushed

Nov 22, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/qinzheng93/GeoTransformer"

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