[Reproduce] KeyNet (Barroso-Laguna et al. ICCV 2019) implementation using PyTorch. (Unofficial)

The implementation of the CVPR 2022 paper: Learning Soft Estimator of Keypoint Scale and Orientation with Probabilistic Covariant Loss.

Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"

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

PopSift is an implementation of the SIFT algorithm in CUDA.

An open library of computer vision algorithms

Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model

PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)

Tensorflow port of LIFT (ECCV 2016), with training code.

Efficient neural feature detector and descriptor

Code release for the ECCV 2016 paper

Sample code to extract descriptors from the HPatches dataset.

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

[ICCV 2019] Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters

My personal note about local and global descriptor

Binary Robust Invariant Scalable Keypoints

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

Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629

[SuperGlue: Learning Feature Matching with Graph Neural Networks] This repo includes PyTorch code for training the SuperGlue matching network on top of SIFT keypoints and descriptors.

The C++ implementation of SuperPoint

[CVPR 2022] Official PyTorch implementation of "Official Self-Supervised Equivariant Learning for Oriented Keypoint Detection"

SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.