vbalnt/tfeat

TFeat descriptor models for BMVC 2016 paper "Learning local feature descriptors with triplets and shallow convolutional neural networks"

47
/ 100
Emerging

TFeat helps computer vision engineers match features between different images. It takes image patches as input and outputs unique descriptors for each patch, which can then be used to find correspondences between images. This is ideal for tasks like image stitching, object recognition, or 3D reconstruction.

150 stars. No commits in the last 6 months.

Use this if you need to reliably identify and match specific visual points or areas across multiple images, even with variations in lighting or viewpoint.

Not ideal if your primary goal is general image classification or object detection rather than precise feature correspondence.

computer-vision image-matching feature-detection 3d-reconstruction robotics-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

150

Forks

44

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 16, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vbalnt/tfeat"

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