Skip to content

rerun-io/kiss-icp

 
 

Repository files navigation

KISS-ICP



Demo   •   Install   •   ROS 2   •   Paper   •   Contact Us

This is fork of the official KISS-ICP repo that uses rerun for visualization.

kiss-icp-pretty.mp4

Install

Building kiss-icp

Create python virtual environment and install kiss-icp:

python3 -m venv venv
. venv/bin/activate
pip install -r requirements.txt
make editable # Builds and installs kiss-icp

Download the NCLT dataset and puts into a directory called data/:

./download_nclt.py

Visualize the dataset:

kiss_icp_pipeline --dataloader nclt data/2013-01-10 --n-scans 150 --jump 600 --deskew --memory-limit 4GB

ROS support

ROS 2
cd ~/ros2_ws/src/ && git clone https://github.com/PRBonn/kiss-icp && cd ~/ros2_ws/ && colcon build --packages-select kiss_icp

For more detailed instructions on the ROS wrapper, please visit this README

ROS 1

⚠️ ⚠️ ROS 1 is deprecated in KISS-ICP and is not officially supported anymore. Upgrade now to ROS 2! ⚠️ ⚠️

The last release that supports ROS 1 is v0.3.0, if you still need ROS 1 support please check that version.

Citation

If you use this library for any academic work, please cite our original paper.

@article{vizzo2023ral,
  author    = {Vizzo, Ignacio and Guadagnino, Tiziano and Mersch, Benedikt and Wiesmann, Louis and Behley, Jens and Stachniss, Cyrill},
  title     = {{KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Way}},
  journal   = {IEEE Robotics and Automation Letters (RA-L)},
  pages     = {1029--1036},
  doi       = {10.1109/LRA.2023.3236571},
  volume    = {8},
  number    = {2},
  year      = {2023},
  codeurl   = {https://github.com/PRBonn/kiss-icp},
}

Contributing

We envision KISS-ICP as a community-driven project, we love to see how the project is growing thanks to the contributions from the community. We would love to see your face in the list below, just open a Pull Request!

Releases

No releases published

Packages

No packages published

Languages

  • Python 55.0%
  • C++ 31.0%
  • Jupyter Notebook 8.1%
  • CMake 5.6%
  • Other 0.3%