# Fast GPU 3D Diffeomorphic Image Registration

arXiv: https://arxiv.org/abs/2004.08893 · HTML: https://mlsanity.com/paper/2004.08893/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2020.

## Built on by (most cited first, 6 of 6)

- [Accurate Point Cloud Registration with Robust Optimal Transport](https://mlsanity.com/paper/2111.00648/) (2021)
- [Learning the Effect of Registration Hyperparameters with HyperMorph](https://mlsanity.com/paper/2203.16680/) (2022)
- [Unsupervised Diffeomorphic Surface Registration and Non-Linear Modelling](https://mlsanity.com/paper/2109.13630/) (2021)
- [CLAIRE -- Parallelized Diffeomorphic Image Registration for Large-Scale Biomedical Imaging Applications](https://mlsanity.com/paper/2209.08189/) (2022)
- [Automatic classification of deformable shapes](https://mlsanity.com/paper/2211.02530/) (2022)
- [VPREG: An Optimal Control Formulation for Diffeomorphic Image Registration Based on the Variational Principle Grid Generation Method](https://mlsanity.com/paper/2510.13109/) (2025)

## Abstract (arXiv)

3D image registration is one of the most fundamental and computationally expensive operations in medical image analysis. Here, we present a mixed-precision, Gauss--Newton--Krylov solver for diffeomorphic registration of two images. Our work extends the publicly available CLAIRE library to GPU architectures. Despite the importance of image registration, only a few implementations of large deformation diffeomorphic registration packages support GPUs. Our contributions are new algorithms to significantly reduce the run time of the two main computational kernels in CLAIRE: calculation of derivatives and scattered-data interpolation. We deploy (i) highly-optimized, mixed-precision GPU-kernels for the evaluation of scattered-data interpolation, (ii) replace Fast-Fourier-Transform (FFT)-based first-order derivatives with optimized 8th-order finite differences, and (iii) compare with state-of-the-art CPU and GPU implementations. As a highlight, we demonstrate that we can register 2563 clinical images in less than 6 seconds on a single NVIDIA Tesla V100. This amounts to over 20× speed-up over the current version of CLAIRE and over 30× speed-up over existing GPU implementations.