Skip to content

Prototype implementation of a non-rigid point cloud registration algorithm using piece-wise tricubic polynomials as transformation model.

License

Notifications You must be signed in to change notification settings

AIT-Assistive-Autonomous-Systems/2D_nonrigid_tricubic_pointcloud_registration

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

2D non-rigid point cloud registration

Introduction

This repository contains a prototype implementation of a 2D non-rigid point cloud registration algorithm. The algorithm is described in the paper "Non-rigid point cloud registration using piece-wise tricubic polynomials as transformation model".

The preprint of the paper can be found here - it can be cited as:

@article{glira2023,
	doi = {10.20944/preprints202310.1120.v1},
	url = {https://doi.org/10.20944/preprints202310.1120.v1},
	year = 2023,
	month = {October},
	publisher = {Preprints},
	author = {Philipp Glira and Christoph Weidinger and Johannes Otepka-Schremmer and Camillo Ressl and Norbert Pfeifer and Michaela Haberler-Weber},
	title = {Non-Rigid Point Cloud Registration Using Piece-Wise Tricubic Polynomials as Transformation Model},
	journal = {Preprints}
}

Also available on View 2D_nonrigid_tricubic_pointcloud_registration on File Exchange.

An efficient 3D implementation of this algorithm written in C++ can be found here.

Minimal example

A minimal example is provided in the test folder. It can be started with:

cd test
minimal_example

This example registers two point clouds of a fish in a non-rigid manner. The result is:

alt

Source of the point clouds: Myronenko, A.; Song, X.; Carreira-Perpinan, M. Non-rigid point set registration: Coherent point drift. Advances in neural information processing systems 2006, 19.

GUI

We have implemented a graphical user interface (GUI) for testing the algorithm - it can be started in the test folder with:

cd test
run_nonrigidRegistrationGUI.m

alt

Requirements

The prototype has been tested with Matlab R2023a. It requires the "Statistics and Machine Learning Toolbox".

About

Prototype implementation of a non-rigid point cloud registration algorithm using piece-wise tricubic polynomials as transformation model.

Topics

Resources

License

Stars

Watchers

Forks

Languages