SuperElastix/elastix

Official elastix repository

What it solves

elastix solves the problem of image registration: finding a spatial transformation that maps one image (the fixed image) onto another (the moving image) so that they align. This is commonly needed in medical imaging to compare images taken at different times, from different devices, or of different patients. The toolbox provides a set of algorithms that optimize similarity metrics to achieve the best alignment.

How it works

elastix is built on the Insight Segmentation and Registration Toolkit (ITK). It uses a modular design: users can configure, test, and compare different registration methods by combining various components like transform types, similarity metrics, and optimization strategies. It offers a command-line interface that allows automated processing of large numbers of datasets through scripting. Additionally, it is available in Python via ITKElastix and in other languages via SimpleElastix, and a Docker image is provided.

Who it’s for

elastix is intended for researchers, developers, and clinicians who need to perform medical image registration. Its command-line interface makes it suitable for batch processing in research workflows, while its wrappers for Python and other languages enable integration into custom applications. It also has plugins for graphical user interfaces like napari and 3D Slicer for interactive use.

Highlights

  • Modular architecture: easily combine different registration algorithms to find the best fit for a specific application.
  • Multi-language support: available in Python, C++, Java, R, Ruby, C#, and Lua via SimpleElastix, and as a Python package ITKElastix.
  • Command-line interface for automated processing of large data sets.
  • Docker image available for easy deployment.
  • Interactive tutorials via Jupyter notebooks.
  • Open source with Apache 2.0 license.
  • Extensive documentation, wiki, and model zoo.

Related

  • Project
    jasonjgardner/blockbench-mcp-plugin

    A plugin and server implementation that exposes Blockbench 3D modeling tools to AI agents via the Model Context Protocol, enabling automated model creation and editing.

  • Project
    EL4CTEO/blender-skills

    Blender Agent Skills is a set of 22 scripts that let AI coding assistants (Claude, Codex, Gemini, Copilot, etc.) control Blender 5.2+ for full‑pipeline 3D asset creation, from modeling to export and QA. Install via a Claude plugin or by cloning and running the provided installer; the skills are then callable by the supported agents.

  • Project
    ghbalf/freecad-ai

    FreeCAD AI is an alpha‑stage FreeCAD workbench that adds a chat‑based AI assistant. It can generate or execute Python code and call a library of 50 built‑in FreeCAD tools to build 3D models from natural‑language prompts, supporting many LLM providers, vision input, session saving, and user‑extendable tools.

  • Project
    HRuiCcc/RuiC-card-skill

    An automated pipeline that transforms text or images into interactive 3D holographic cards with depth and shimmer, delivering both a web viewer and an editable Blender project.