📝Awesome and classical image retrieval papers

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

My personal note about local and global descriptor

Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)

Code for the CVPR2021 paper "Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition"

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

PyTorch Implementation of "Large-Scale Image Retrieval with Attentive Deep Local Features"

Open Source Graph Neural Net Based Pipeline for Image Matching

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

Code and weights for local feature affine shape estimation paper "Repeatability Is Not Enough: Learning Discriminative Affine Regions via Discriminability"

ELSED: Enhanced Line SEgment Drawing

Comparative Evaluation of Hand-Crafted and Learned Local Features

Baselines for the Image Matching Benchmark and Challenge

PyTorch implementation of SIFT descriptor

🚀🚀 Revisiting Binary Local Image Description for Resource Limited Devices

[CVPR 2023] SFD2: Semantic-guided Feature Detection and Description. Embedding semantics into local features implicitly for long-term visual localization

[CVPR2022] Decoupling Makes Weakly Supervised Local Feature Better

HOW local descriptors

MODS (Matching On Demand with view Synthesis) is algorithm for wide-baseline matching.