pmwenzel

Pointnet_Pointnet2_pytorch

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

Pseudo_Lidar_V2

(ICLR) Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving

LoFTR

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

OverlapPredator

[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.

unsupervisedRR

[CVPR 2021 - Oral] UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering

differentiable_volumetric_rendering

This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"

keypoint-style-transfer

Implementation of the paper "Style Transfer for Keypoint Matching under Adverse Condition"

disk

Disk code release

torch-points3d

Pytorch framework for doing deep learning on point clouds.

RLLReg

Registration Loss Learning for Deep Probabilistic Point Set Registration

kapture-localization

Provide mapping and localization pipelines based on kapture format

gradslam

gradslam is an open source differentiable dense SLAM library for PyTorch

rpg_vid2e

Open source implementation of CVPR 2020 "Video to Events: Recycling Video Dataset for Event Cameras"

fine-grained-segmentation-networks

Code for the ICCV paper "Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization"

FreeViewSynthesis

Code repository for "Free View Synthesis", ECCV 2020.

image-box-overlap

[ECCV 2020] Training neural networks to predict visual overlap of images, through interpretable non-metric box embeddings

nonechucks

Deal with bad samples in your dataset dynamically, use Transforms as Filters, and more!

DejaVu_Features

Hierarchical-Localization

Visual localization made easy with hloc

kapture

kapture is a file format as well as a set of tools for manipulating datasets, and in particular Visual Localization and Structure from Motion data.

arxiv-latex-cleaner

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

IndRNN_pytorch

Independently Recurrent Neural Networks (IndRNN) implemented in pytorch.

FCGF

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

fonts

Patched fonts for Powerline users.

DeFeat-Net

OpenIBL

[ECCV-2020 (spotlight)] Self-supervising Fine-grained Region Similarities for Large-scale Image Localization. 🌏 PyTorch open-source toolbox for image-based localization (place recognition).

S2DHM

Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization (3DV 2019)

TEASER-plusplus

A fast and robust point cloud registration library

visuallocalizationbenchmark

DeepGlobalRegistration

[CVPR 2020 Oral] A differentiable framework for 3D registration