AaltoVision/DGC-Net

A PyTorch implementation of "DGC-Net: Dense Geometric Correspondence Network"

39
/ 100
Emerging

This project helps computer vision researchers and practitioners accurately match individual pixels between two different images of the same scene, even when the viewpoints change significantly. You input two images, and it outputs a dense map showing how each pixel in the first image corresponds to a pixel in the second. This is ideal for anyone working on tasks requiring precise alignment or understanding of visual changes across images.

206 stars. No commits in the last 6 months.

Use this if you need to find precise pixel-level correspondences between two images, particularly when the camera angle or perspective has shifted.

Not ideal if you're looking for an off-the-shelf application for commercial use, as its license is for non-commercial purposes only and it requires a developer to integrate.

computer-vision image-matching 3d-reconstruction robot-navigation augmented-reality
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

206

Forks

18

Language

Jupyter Notebook

License

Last pushed

Oct 12, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AaltoVision/DGC-Net"

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