flexcloud 1.0.2

Direct, modular georeferencing and drift-correction of point cloud maps

FlexCloud

Georeferencing of Point Cloud Maps

Full documentation: https://TUMFTM.github.io/FlexCloud

Installation

pip install flexcloud

Supported platform: Ubuntu 24.04 on x86_64 with CPython 3.12. The published PyPI wheel is built for manylinux_2_39_x86_64 / cp312 only. On other platforms, use the Docker image or build from source.

Usage

All algorithm parameters are CLI flags with reasonable defaults.

Keyframe Interpolation

flexcloud-keyframe-interpolation -h

ros2 run flexcloud keyframe_interpolation

Georeferencing

flexcloud-georeferencing -h

ros2 run flexcloud georeferencing

Documentation

For more details on the implementation and available features, refer to the full documentation hosted on GitHub pages: https://TUMFTM.github.io/FlexCloud

Test Data

The data was recorded by the TUM Autonomous Motorsport Team during the Abu Dhabi Autonomous Racing League 2025. The LiDAR/SLAM trajectory is created using glim. The reference trajectory presents raw data from the RTK-corrected GNSS-signal of the vehicle.

Developers

• Maximilian Leitenstern, Institute of Automotive Technology, School of Engineering and Design, Technical University of Munich, 85748 Garching, Germany
• Marko Alten (student research project)
• Christian Bolea-Schaser (student research project)

Citation

If you use this repository for any academic work, please consider citing our paper (preprint):

@conference{leitenstern2025flexcloud,
author={Maximilian Leitenstern and Marko Alten and Christian Bolea-Schaser and Dominik Kulmer and Marcel Weinmann and Markus Lienkamp},
title={FlexCloud: Direct, Modular Georeferencing and Drift-Correction of Point Cloud Maps},
booktitle={Proceedings of the 11th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS},
year={2025},
pages={157-165},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013359600003941},
isbn={978-989-758-745-0},
}