Strategies for Robust Deep Learning Based Deformable Registration

Joel Honkamaa, Pekka Marttinen
10/27/2025
cs.CV

No confident code implementation found for this paper.

Abstract

Deep learning based deformable registration methods have become popular in recent years. However, their ability to generalize beyond training data distribution can be poor, significantly hindering their usability. LUMIR brain registration challenge for Learn2Reg 2025 aims to advance the field by evaluating the performance of the registration on contrasts and modalities different from those included in the training set. Here we describe our submission to the challenge, which proposes a very simple idea for significantly improving robustness by transforming the images into MIND feature space before feeding them into the model. In addition, a special ensembling strategy is proposed that shows a small but consistent improvement.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Surrogate Supervision for Robust and Generalizable Deformable Image Registration

88% match2025

MsMorph: An Unsupervised pyramid learning network for brain image registration

87% match1 repo42024

Fine-Tuning TransMorph with Gradient Correlation for Anatomical Alignment

86% match2024

Recurrent Inference Machine for Medical Image Registration

85% match2024

Disentangling Progress in Medical Image Registration: Beyond Trend-Driven Architectures towards Domain-Specific Strategies

85% match1 repo172025

UTSRMorph: A Unified Transformer and Superresolution Network for Unsupervised Medical Image Registration

84% match1 repo212024

Cite this paper

@article{honkamaa2025strategies,
  title  = {Strategies for Robust Deep Learning Based Deformable Registration},
  author = {Joel Honkamaa and Pekka Marttinen},
  year   = {2025},
  eprint = {2510.23079},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.23079v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.23079.svg)](https://codeofpaper.com/paper/2510.23079)

Discussion