Rémi Pautrat

Efficient neural feature detector and descriptor

Training library for local feature detection and matching

Local Invariance Selection at Runtime for Descriptors (LISRD)

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

Python transparent bindings for LSD (Line Segment Detector)

No description.

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

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

Python bindings for COLMAP estimators

VS-Net: Voting with Segmentation for Visual Localization

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

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

Open Source Differentiable Computer Vision Library

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

No description.

Open3D: A Modern Library for 3D Data Processing

Personal Pytorch framework to train and run deep learning algorithms

My personal website

pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.

A library for flexible voxel-based mapping, mainly focusing on truncated and Euclidean signed distance fields.

Python tools for working with KITTI data.

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

Holistically-Attracted Wireframe Parsing

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

No description.

Visual localization made easy

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

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

A PyTorch port of the Neural 3D Mesh Renderer