# voxelmorph/voxelmorph

Unsupervised Learning for Image Registration

Repository: https://github.com/voxelmorph/voxelmorph
Canonical: https://ross.abutalabs.com/products/voxelmorph
Language: Python
License: Apache-2.0
License Family: permissive
Topics: image-registration, image-alignment, machine-learning, deep-learning, probabilistic, diffeomorphism, unsupervised-learning, optical-flow
Last push: 2026-08-17T22:35:41+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 100
- inputs: {"age_days": 3033, "days_push": 16, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2748, forks 640 (observed 2026-08-28T04:07:17.786515+00:00)

## What it is
VoxelMorph is a Python library for learning-based image registration and alignment, using unsupervised deep learning to model deformations between images. It offers both a PyTorch version under active development and a stable TensorFlow branch, with pre-trained models and tutorials for medical imaging tasks.

## Use cases
- register medical images like MRI or CT scans
- align 3D brain volumes with deep learning
- train an unsupervised image registration model
- build anatomical templates with atlas construction
- compute diffeomorphic warps between images
- perform cross-modal registration like CT to MRI

## When to choose
- you need fast, learning-based registration of 2D or 3D medical images
- you want unsupervised registration without paired ground-truth deformations
- you need diffeomorphic or probabilistic deformation models
- you want pre-trained models like SynthMorph for brain MRI alignment

## When to avoid
- you need simple rigid or affine registration of a few images without training
- you require a fully stable API and prefer not to track active development
- your project does not involve deep learning or GPU compute
- you need registration for non-volumetric data like plain documents

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, image-processing, deep-learning
- domain: machine-learning, deep-learning, healthcare, image-processing
- platform: python
- tags: image-registration, medical-imaging, diffeomorphism, unsupervised-learning, pytorch, tensorflow, deformable-registration, synthmorph

## Member repositories
- voxelmorph/voxelmorph (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:17.786515+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:19:00.475512+00:00, confidence not recorded.
  - readme: https://github.com/voxelmorph/voxelmorph (fetched 2026-08-28T04:07:17.786515+00:00, sha 8d50c6d3bf3f)
  - registry_pypi: https://pypi.org/pypi/voxelmorph/json (fetched 2026-08-29T09:56:57.108562+00:00, sha 44670e0aa141)
- Data as of 2026-08-30T08:39:29.467469+00:00.