hyenal/coam

Official repository of 'Co-Attention for Conditioned Image Matching'

32
/ 100
Emerging

This project helps computer vision researchers and practitioners accurately match specific features or regions between two different images, even when one image is distorted, stylized, or taken from a different viewpoint. You provide a pair of images and optionally a 'conditioning' image that guides the matching process, and the system identifies corresponding points or areas across them. It is designed for those working with visual recognition, 3D reconstruction, or visual localization tasks.

No commits in the last 6 months.

Use this if you need robust and precise image feature matching, especially when dealing with changes in viewpoint, lighting, or artistic stylization between image pairs.

Not ideal if you are looking for a general-purpose image search or object detection tool rather than fine-grained feature correspondence.

computer-vision 3d-reconstruction visual-localization image-matching feature-correspondence
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

37

Forks

9

Language

Python

License

Last pushed

May 23, 2021

Commits (30d)

0

Get this data via API

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

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