Skip to content
RobothecaBeta
Log in

KISS-Matcher

  • Software
  • Navigation and mapping
  • Library

A fast, scalable point cloud registration library in C++ and Python that aligns two 3D point clouds, with ROS2 and robust outlier rejection built on the ROBIN package.

Made by MIT-SPARK.

Source on GitHub: github.com/MIT-SPARK/KISS-Matcher (opens in a new tab). Facts read at commit 8b58b11 (opens in a new tab).

Licenses

Code
MIT (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit 8b58b11 (opens in a new tab), on 16 Oct 2026.

Commercial use
Yes

What it does

  • Provides C++ and Python implementations for registering two 3D point clouds, with example code for each.
  • Can be installed via make deps and make cppinstall, or with pip install kiss-matcher from PyPI.
  • Includes a quickstart script that runs registration on synthetic data and reports rotation and translation error.
  • Includes an optional visualization demo for real point clouds, available through the viz extra.
  • Depends on ROBIN for outlier rejection and is linked automatically during the C++ build.
  • Is described as a community-driven project that accepts contributions via pull requests.

Written by Robotheca from the project's README (opens in a new tab) at commit 8b58b11.

Getting started

Difficulty
Advanced
Hardware it needs, as the project states it
Ubuntu or Debian (apt-get toolchain) or macOS (Apple Silicon or Intel, via Homebrew with llvm and libomp); the PyPI wheel targets Linux x86_64 manylinux_2_28+ and macOS 14+ arm64, and other platforms build from source.

Maintenance

Status
Active: a commit in the last 90 days
Newest commit
13 Aug 2026 on main
Latest release
KISS-Matcher v1.0.2 (10 May 2026)

Checked on GitHub on 16 Oct 2026.

Links

Robots that can run it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.