cvg/FlexGlue
Model
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 2 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A feature matcher that finds correspondences between two images using dense features from a DINOv3-ConvNeXt backbone and a transformer. It works with detected keypoints, dense grids, or no keypoints, and predicts whether an image pair is covisible at all.
Who it's for
Computer vision researchers and developers building image matching, structure-from-motion or visual localization pipelines in Python
How to use it
Install
python -m pip install -e .From its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up cvg/FlexGlue in my project. Follow its README: https://github.com/cvg/FlexGlue. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
21,780 GitHub repos watched and ranked every hour. Figures as of 28 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/cvg/FlexGlue?ref=badge)Similar repos
- patch-gg/anymove
Turns one AI-generated video of a creature, filmed from two cameras in one frame, into a GLB animation for a rigged 3D model. A trained DINOv2 reader finds the joints in both views, and the rig is fit
- bagusprts/RoughGlue
A real-time data processing gateway service that integrates geo-enabled machine learning frameworks. The README is generic and does not detail specific endpoints or features. Configured via environmen
- solidsf-inc/solidcv
A pure-Rust computer vision library with no C++ or FFI dependencies, offering OpenCV-style APIs for image processing, stereo reconstruction, and 3D scene analysis. It includes features aimed at VLM pa
- CharlesFeng0314/JEV_sees
Python library that detects, tracks and labels objects in images, video and RGB-D camera streams using local vision models, then sends a question about each object to the JEV API and returns structure
- patch-gg/trompe
Browser-based tool that textures a whole game level from a gray blockout. It plans camera views where a player can stand, paints each view with image models hosted on fal, projects the paintings back
- xibushu/UniForge3D
Official implementation of a method that generates complete 3D assets from sparse, unposed multi-view images. It jointly models reconstruction and generation in a shared anchor-guided space and uses s