JanghunHyeon/PCLoc

Pose Correction for Highly Accurate Visual Localization in Large-scale Indoor Spaces (ICCV 2021)

27
/ 100
Experimental

This project helps autonomous robots and augmented/mixed reality systems accurately pinpoint their location within complex indoor environments. It takes a query image of a space and a database of images from that space, then provides a highly precise estimate of the camera's 3D position and orientation. This tool is for engineers or researchers developing robust visual localization capabilities for indoor navigation and AR applications.

No commits in the last 6 months.

Use this if you need to achieve highly accurate 3D pose estimation for visual localization in large-scale indoor settings, especially when dealing with sparse image databases.

Not ideal if your application requires outdoor localization or if you do not have a pre-existing image database of the indoor environment.

robot-navigation augmented-reality indoor-positioning visual-localization mobile-robotics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

66

Forks

7

Language

Python

License

Last pushed

Jun 27, 2023

Commits (30d)

0

Get this data via API

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

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