LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
-
Updated
Feb 18, 2026 - Python
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!
🎓Automatically Update CV Papers Daily using Github Actions
🤗 image matching webui
[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.
Training library for local feature detection and matching
🔥SLAM, VIsual localization, keypoint detection, Image matching, Pose/Object tracking, Depth/Disparity/Flow Estimation, 3D-graphic, etc. related papers and code
GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)
Wrapper of 50+ image matching models with a unified interface
Code release for CVPR'24 submission 'OmniGlue'
Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)
[CVPR 2025] MINIMA: Modality Invariant Image Matching
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.
Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"
[CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation
Bibliographic list for papers of image matching
A personal list of papers and resources of image matching and pose estimation, including perspective images and panoramas.
Open Source Graph Neural Net Based Pipeline for Image Matching
Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".
Add a description, image, and links to the image-matching topic page so that developers can more easily learn about it.
To associate your repository with the image-matching topic, visit your repo's landing page and select "manage topics."