#image-matching Repositories
Discover 19 active open source GitHub repositories tagged with #image-matching, accumulating 24,000 total stars (averaging 1,263 stars per project). Leading this topic is cvg/LightGlue with 4,887 stars.
19 repositories total
Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!
[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.
Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", TPAMI 2026.
GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)
SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.
This is a toolbox repository to help evaluate various methods that perform image matching from a pair of images.
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM software. Supports high-resolution formats and images with rotations. Both CLI and GUI are supported.
Public release of the Image Matching Benchmark: https://image-matching-challenge.github.io
Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"
Frequently Asked Questions
What is the most popular #image-matching repository on GitHub?
The top ranked open source #image-matching project on GitHub is cvg/LightGlue with 4,887 stars. LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
Which programming languages are most used in #image-matching repositories?
Among the top ranked #image-matching projects on GitHub, the most common programming languages are Python, Jupyter Notebook, Gnuplot.
How is the #image-matching repository ranking calculated?
We track 19 active open source repositories tagged with #image-matching (500+ stars), totaling 24,000 stars with an average of 1,263 stars per repository. Rankings update daily from the GitHub API.