The open-source tool for building high-quality datasets and computer vision models

This is a toolbox repository to help evaluate various methods that perform image matching from a pair of images.

Desktop Backup Client for Borg

Kernel Point Convolution implemented in PyTorch

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

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

Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization

Tensors and Dynamic neural networks in Python with strong GPU acceleration

COLMAP - Structure-from-Motion and Multi-View Stereo

USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds

Point Cloud Library (PCL)

Fully Convolutional Geometric Features: Fast and accurate 3D features for registration and correspondence.

🌍 C++11 ply 3d mesh format importer & exporter

🍻 Default formulae for the missing package manager for macOS

Open Source Visual Servoing Platform

RPM-Net: Robust Point Matching using Learned Features (CVPR2020)

SemanticKITTI API for visualizing dataset, processing data, and evaluating results.

Open Source Computer Vision Library