ssssjiang

event-based_vision_resources

e2calib

CVPRW 2021: How to calibrate your event camera

hdl_graph_slam

3D LIDAR-based Graph SLAM

HoloLens2ForCV

Sample code and documentation for using the Microsoft HoloLens 2 for Computer Vision research.

Learning-to-See-in-the-Dark

Learning to See in the Dark. CVPR 2018

raybender

Fast CPU rendering in Python using the Intel® Embree backend

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

NPYViewer

Load and view .npy files containing 2D and 1D NumPy arrays.

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

disk

Disk code release

NeuralRecon

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

visloc_pseudo_gt_limitations

cs344

Introduction to Parallel Programming class code

d2-net

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

OANet

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

folly

An open-source C++ library developed and used at Facebook.

SuperGluePretrainedNetwork

C++-compatible fork of SuperGlue

SuperGluePretrainedNetwork

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

cnnimageretrieval-pytorch

CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch

Open3D

Open3D: A Modern Library for 3D Data Processing

pytorch-superpoint

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

vilib

CUDA Visual Library by RPG

ElasticFusion

Real-time dense visual SLAM system

SOLD2

Joint deep network for feature line detection and description

RansacLib

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

ORB_Segmentation

使用语义分割将图像中的人分离出来,将原始图像中提取的ORB特征点落在人身上的剔除(用于SLAM的位姿估计).

packnet-sfm

TRI-ML Monocular Depth Estimation Repository

KP3D

Code for "Self-Supervised 3D Keypoint Learning for Ego-motion Estimation"

Map-based-Visual-Localization

A general framework for map-based visual localization. It contains 1) Map Generation which support traditional features or deeplearning features. 2) Hierarchical-Localizationvisual in visual(points or line) map. 3)Fusion framework with IMU, wheel odom and GPS sensors.

reverse-interview-zh

技术面试最后反问面试官的话