There are 1 repository under multi-view-geometry topic.
LiveScan3D is a system designed for real time 3D reconstruction using multiple Azure Kinect or Kinect v2 depth sensors simultaneously at real time speed.
Distributed and Graph-based Structure from Motion. This project includes the official implementation of our Pattern Recognition 2020 paper: Graph-Based Parallel Large Scale Structure from Motion.
[NeurIPS 2023] Code for "Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives"
This work generates 2D and 3D landmark labels from videos with only two or three uncalibrated, handheld cameras moving in the wild. NeurIPS 2022.
Images dataset for 3D reconstruction
The EYELib: A matlab-python library for Single View Metrology and auto-calibration algorithms and methods
a library that clusters set of images with poses into clusters for easier mvs
Some functions to work with Lie groups SO(3) and SE(3). State Estimation for Robotics
Camera calibration tool in Python + OpenCV
[WACV-2020] Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency
深蓝学院视觉slam理论与实践 Implementation of Basic Visual SLAM Algorithms
Code accompanying 'A linear method for camera pair self-calibration' paper about camera pair self-calibration and metric reconstruction starting from a projective reconstruction, assuming different and varying focal lengths
Multi-view pose estimation with flexible mixtures of parts and adaptive viewpoint selection
This repository contains my paper reviews, solutions and code submissions for projects completed as part of CMSC848F during Fall 2023. Each project is organized in its own folder, with accompanying documentation and any necessary resources.
A cheap solution to VR tracking using multiple Wi-Fi based cameras and a light
Experimental code for 3D reconstruction from multiple images
My implementation of algorithms used in Computer Vision.
Jupyter notebooks on 3D vision