mlsanityData to 14 Oct 2026

RealKeyMorph: Keypoints in Real-world Coordinates for Resolution-agnostic Image Registration

arXiv 2506.10344 ↗First posted 12 Jun 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Many real-world settings require registration of a pair of medical images that differ in spatial resolution, which may arise from differences in image acquisition parameters like pixel spacing, slice thickness, and field-of-view. However, all previous machine learning-based registration techniques resample images onto a fixed resolution. This is suboptimal because resampling can introduce artifacts due to interpolation. To address this, we present RealKeyMorph (RKM), a resolution-agnostic method for image registration. RKM is an extension of KeyMorph, a registration framework which works by training a network to learn corresponding keypoints for a given pair of images, after which a closed-form keypoint matching step is used to derive the transformation that aligns them. To avoid resampling and enable operating on the raw data, RKM outputs keypoints in real-world coordinates of the scanner. To do this, we leverage the affine matrix produced by the scanner (e.g., MRI machine) that encodes the mapping from voxel coordinates to real world coordinates. By transforming keypoints into real-world space and integrating this into the training process, RKM effectively enables the extracted keypoints to be resolution-agnostic. In our experiments, we demonstrate the advantages of RKM on the registration task for orthogonal 2D stacks of abdominal MRIs, as well as 3D volumes with varying resolutions in brain datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 75 references that are in the map. First posted on arXiv 12 Jun 2025.

Builds on

30 of 75 references.

References · 30

  1. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  2. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  3. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 662
  4. 2016LIFT: Learned Invariant Feature Transformcited by 306
  5. 2021SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retrainingcited by 237
  6. 2019Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfacescited by 186
  7. 2020TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learningcited by 177
  8. 2017Learning to Find Good Correspondencescited by 176
  9. 2018A Deep Learning Framework for Unsupervised Affine and Deformable Image Registrationcited by 160
  10. 2018LF-Net: Learning Local Features from Imagescited by 151
  11. 2020SynthMorph: learning contrast-invariant registration without acquired imagescited by 140
  12. 2019Deep Learning in Medical Image Registration: A Surveycited by 124
18 more
  1. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 118
  2. 2018Unsupervised Learning for Fast Probabilistic Diffeomorphic Registrationcited by 116
  3. 2017Quicksilver: Fast Predictive Image Registration - a Deep Learning Approachcited by 113
  4. 2019Deep Learning in Medical Image Registration: A Reviewcited by 98
  5. 2021HyperMorph: Amortized Hyperparameter Learning for Image Registrationcited by 85
  6. 2018Learning a Probabilistic Model for Diffeomorphic Registrationcited by 62
  7. 2014TILDE: A Temporally Invariant Learned DEtectorcited by 55
  8. 2019Unsupervised Deformable Registration for Multi-Modal Images via Disentangled Representationscited by 52
  9. 2019Dual-Stream Pyramid Registration Networkcited by 52
  10. 2019Image-and-Spatial Transformer Networks for Structure-Guided Image Registrationcited by 36
  11. 2022SVoRT: Iterative Transformer for Slice-to-Volume Registration in Fetal Brain MRIcited by 26
  12. 2016Learning Covariant Feature Detectorscited by 25
  13. 2023A Robust and Interpretable Deep Learning Framework for Multi-modal Registration via Keypointscited by 25
  14. 2021SAME: Deformable Image Registration based on Self-supervised Anatomical Embeddingscited by 21
  15. 2018Generative Adversarial Networks for MR-CT Deformable Image Registrationcited by 12
  16. 2020Volumetric landmark detection with a multi-scale shift equivariant neural networkcited by 9
  17. 2018Keypoint Transfer for Fast Whole-Body Segmentationcited by 8
  18. 2024Diffeomorphic Transformer-based Abdomen MRI-CT Deformable Image Registrationcited by 1

Built on by

Not cited yet.