MIT-SPARK/KISS-Matcher

KISS-Matcher: Fast, Robust, and Scalable Registration + ROS2 SLAM examples

What it solves

KISS-Matcher provides a fast and robust method for point cloud registration, which is the process of aligning two or more 3D point clouds to determine the relative transformation (rotation and translation) between them. It aims to be simple and scalable for real-world applications.

How it works

While the README does not detail the internal mathematical algorithms, it integrates with the ROBIN package for outlier rejection and leverages small_gicp to enhance pipeline efficiency. It is implemented in both C++ and Python, allowing for flexible integration into robotics and mapping systems.

Who it’s for

This tool is designed for robotics researchers and engineers working with 3D perception, LiDAR SLAM, and point cloud processing.

Highlights

  • Dual-Language Support: Available as a C++ library and a PyPI-installable Python package.
  • Cross-Platform: Supports Ubuntu/Debian and macOS (including Apple Silicon).
  • Out-of-the-box Installation: Includes automated dependency management via Makefiles.
  • Visualization: Offers optional 3D visualization support via the viser library in Python.

Related

  • Project
    norlab-ulaval/libpointmatcher

    A modular C++ library with Python bindings that implements the Iterative Closest Point (ICP) algorithm for aligning 3D point clouds in robotics and computer vision.

  • Project
    neka-nat/probreg

    A library for point cloud registration using probabilistic models, offering a more robust alternative to ICP for both rigid and non-rigid transformations.

  • Project
    koide3/small_gicp

    A highly optimized, parallelized C++ library for fine point cloud registration (ICP, GICP, VGICP) designed for high-speed 3D alignment.

  • Project
    PRBonn/kiss-icp

    A LiDAR Odometry pipeline that provides accurate and robust registration without requiring manual parameter tuning.

  • Project
    ch-sa/labelCloud

    A lightweight 3D bounding box labeling tool for point clouds, used to generate training data for 3D object detection and 6D pose estimation.