rpautrat

SuperPoint

Efficient neural feature detector and descriptor

LISRD

Local Invariance Selection at Runtime for Descriptors (LISRD)

homography_est

Light-weight library to perform homography estimation with RANSAC from point, line or point-line correspondences

pytlsd

Python transparent bindings for LSD (Line Segment Detector)

pycolmap

Python bindings for COLMAP estimators

visuallocalizationbenchmark

DL_framework

Personal Pytorch framework to train and run deep learning algorithms

dsacstar

DSAC* for Visual Camera Re-Localization (RGB or RGB-D)

kornia

Open Source Differentiable Computer Vision Library

OANet

Implementation of ICCV19 Paper "Learning Two-View Correspondences and Geometry Using Order-Aware Network"

Open3D

Open3D: A Modern Library for 3D Data Processing

r2d2

RansacLib

Template-based implementation of RANSAC and its variants in C++

SuperGluePretrainedNetwork

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

SuperPointPretrainedNetwork

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

VS-Net

VS-Net: Voting with Segmentation for Visual Localization

CannyEdgePytorch

d2_net

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

GIFT

Code for "GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs" NeurIPS 2019

glue-factory

Training library for local feature detection and matching

hawp

Holistically-Attracted Wireframe Parsing

Hierarchical-Localization

Visual localization made easy

neural_renderer

A PyTorch port of the Neural 3D Mesh Renderer

progressive-x

The Progressive-X algorithm proposed in paper: Daniel Barath and Jiri Matas; Progressive-X: Efficient, Anytime, Multi-Model Fitting Algorithm, International Conference on Computer Vision, 2019. It is available at https://arxiv.org/pdf/1906.02290

pykitti

Python tools for working with KITTI data.

TP-LSD

Adaptation of the original "TP-LSD: Tri-points based line segment detector" with more recent torch/cuda versions