Chang Chen(陈常)'s repositories
multical
Multi-camera calibration using one or more calibration patterns
UmeTrack
UmeTrack Unified multi-view end-to-end hand tracking for VR
NeuralPassthrough
This repository provides source code, trained neural network model and dataset for our NeuralPassthrough work that is published at SIGGRAPH 2022.
ORB_SLAM3
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
cardboard-java
Google Cardboard
rapidjson
A fast JSON parser/generator for C++ with both SAX/DOM style API
siml
Machine Learning algorithms implemented from scratch
Activity-Recognition
Human Activity Recognition from IMU data using Deep Learning (Tensorflow)
dip18
Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time
cpp-project-template
Repository Templates for C++ Projects
PL-VINS
PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Features
ai-imu-dr
AI-IMU Dead-Reckoning
ORB-SLAM2-DualCam
Modified ORB-SLAM2 to run on dual cameras (without common-view)
PPGNet
Source code for our CVPR 2019 paper - PPGNet: Learning Point-Pair Graph for Line Segment Detection
svo_edgelet
A more robust SVO with edgelet feature
vig-init
Rapid and Robust Monocular Visual-Inertial Initialization with Gravity Estimation via Vertical Edges
popsift
PopSift is an implementation of the SIFT algorithm in CUDA.
ronin
RoNIN: Robust Neural Inertial Navigation in the Wild
MASAT_IG_for_SLAM
Finding sufficient initial guesses for offline SLAM
Key.Net
Code for the ICCV19 paper Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters
okvis
OKVIS: Open Keyframe-based Visual-Inertial SLAM.
ORB_SLAM2
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
open_vins
An open source platform for visual-inertial navigation research.
monodepth
Unsupervised single image depth prediction with CNNs
hardnet
Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"
Kimera-VIO
Visual Inertial Odometry with SLAM capabilities and 3D Mesh generation.
SuperPoint_SLAM
SuperPoint + ORB_SLAM2