NeurAI-Lab/biHomE

This is the official repo for the CVPR 2021 IMW paper: "Perceptual Loss for Robust Unsupervised Homography Estimation"

35
/ 100
Emerging

This project helps computer vision researchers and practitioners accurately align images, even when illumination or viewpoints change significantly. It takes two images of the same scene, possibly captured under different conditions or angles, and outputs the mathematical transformation (homography) needed to perfectly overlap them. This is useful for tasks like creating panoramas, video stabilization, or image stitching.

No commits in the last 6 months.

Use this if you need to precisely align images that might have drastic differences in lighting or viewing angles, and existing methods struggle with robustness.

Not ideal if you're dealing with images that are fundamentally different or don't represent the same scene, as it's designed for aligning related views.

image-registration computer-vision image-stitching camera-pose-estimation photogrammetry
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

38

Forks

5

Language

Python

License

MIT

Last pushed

Jan 31, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NeurAI-Lab/biHomE"

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