SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

Visual localization made easy with hloc

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

A clean and concise Python implementation of SIFT (Scale-Invariant Feature Transform)

🤗 image matching toolbox 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.

[CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation

[CVPR 2020, Oral] MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask

ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO

Patch2Pix: Epipolar-Guided Pixel-Level Correspondences [CVPR2021]

Code to easily try 30 (and growing) different image matching methods

SuperPoint and SuperGlue with TensorRT. Deploy with C++.

💎 "Marker-less Augmented Reality" with OpenCV and OpenGL.

A framework for building high-performance real-time multiple object trackers

Feature Detection and Matching with SIFT, SURF, KAZE, BRIEF, ORB, BRISK, AKAZE and FREAK through the Brute Force and FLANN algorithms using Python and OpenCV

Python (Pytorch) and Matlab (MatConvNet) implementations of CVPR 2021 Image Matching Workshop paper DFM: A Performance Baseline for Deep Feature Matching

Interactive code for image similarity using SIFT algorithm

基于opencv的图像识别基础库

Integrate SuperPoint and LightGlue into OpenCV image stitching or Matching algorithm