placeforyiming/CVPR21-Deep-Lucas-Kanade-Homography

A generic pipeline to align multimodal image pairs from different sensors by extending Lucas-Kanade on feature maps. CVPR2021

38
/ 100
Emerging

This project helps align images from different sensors or conditions, like satellite maps with regular street views or images of the same location taken in different seasons. It takes two distinct images of the same scene and outputs a precisely aligned composite. This is useful for researchers or engineers working with geospatial data, remote sensing, or computer vision.

145 stars. No commits in the last 6 months.

Use this if you need to accurately combine or compare images captured from different sources or at varying times, where traditional alignment methods struggle with visual differences.

Not ideal if you are working with images that are already visually very similar or if you don't require highly precise pixel-level alignment across different modalities.

geospatial-analysis remote-sensing image-registration computer-vision multispectral-imaging
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 20 / 25

How are scores calculated?

Stars

145

Forks

31

Language

Python

License

Last pushed

Jun 24, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/placeforyiming/CVPR21-Deep-Lucas-Kanade-Homography"

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