# Deep learning based geometric registration for medical images: How accurate can we get without visual features?

arXiv: https://arxiv.org/abs/2103.00885 · HTML: https://mlsanity.com/paper/2103.00885/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 1 Mar 2021.

## Builds on (most cited first, 15 of 15)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networks](https://mlsanity.com/paper/2006.16148/) (2020)
- [FLOT: Scene Flow on Point Clouds Guided by Optimal Transport](https://mlsanity.com/paper/2007.11142/) (2020)
- [DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation](https://mlsanity.com/paper/1904.08465/) (2019)
- [Closing the Gap between Deep and Conventional Image Registration using Probabilistic Dense Displacement Networks](https://mlsanity.com/paper/1907.10931/) (2019)
- [Estimation of Large Motion in Lung CT by Integrating Regularized Keypoint Correspondences into Dense Deformable Registration](https://mlsanity.com/paper/1807.00467/) (2018)

## Built on by (most cited first, 10 of 10)

- [Accurate Point Cloud Registration with Robust Optimal Transport](https://mlsanity.com/paper/2111.00648/) (2021)
- [Unsupervised 3D registration through optimization-guided cyclical self-training](https://mlsanity.com/paper/2306.16997/) (2023)
- [Adapting the Mean Teacher for keypoint-based lung registration under geometric domain shifts](https://mlsanity.com/paper/2207.00371/) (2022)
- [Robust-DefReg: A Robust Deformable Point Cloud Registration Method based on Graph Convolutional Neural Networks](https://mlsanity.com/paper/2306.04701/) (2023)
- [Unsupervised Deformable Image Registration with Structural Nonparametric Smoothing](https://mlsanity.com/paper/2506.10813/) (2025)
- [DefTransNet: A Transformer-based Method for Non-Rigid Point Cloud Registration in the Simulation of Soft Tissue Deformation](https://mlsanity.com/paper/2502.06336/) (2025)
- [A Survey of Medical Point Cloud Shape Learning: Registration, Reconstruction and Variation](https://mlsanity.com/paper/2508.03057/) (2025)
- [A denoised Mean Teacher for domain adaptive point cloud registration](https://mlsanity.com/paper/2306.14749/) (2023)
- [SynBench: A Synthetic Benchmark for Non-rigid 3D Point Cloud Registration](https://mlsanity.com/paper/2409.14474/) (2024)
- [Interpretable deformable image registration: A geometric deep learning perspective](https://mlsanity.com/paper/2412.13294/) (2024)

## Abstract (arXiv)

As in other areas of medical image analysis, e.g. semantic segmentation, deep learning is currently driving the development of new approaches for image registration. Multi-scale encoder-decoder network architectures achieve state-of-the-art accuracy on tasks such as intra-patient alignment of abdominal CT or brain MRI registration, especially when additional supervision, such as anatomical labels, is available. The success of these methods relies to a large extent on the outstanding ability of deep CNNs to extract descriptive visual features from the input images. In contrast to conventional methods, the explicit inclusion of geometric information plays only a minor role, if at all. In this work we take a look at an exactly opposite approach by investigating a deep learning framework for registration based solely on geometric features and optimisation. We combine graph convolutions with loopy belief message passing to enable highly accurate 3D point cloud registration. Our experimental validation is conducted on complex key-point graphs of inner lung structures, strongly outperforming dense encoder-decoder networks and other point set registration methods. Our code is publicly available at https://github.com/multimodallearning/deep-geo-reg.