# NCF: Neural Correspondence Field for Medical Image Registration

arXiv: https://arxiv.org/abs/2503.00760 · HTML: https://mlsanity.com/paper/2503.00760/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 2 Mar 2025.

## Builds on (most cited first, 7 of 7)

- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration](https://mlsanity.com/paper/2104.06468/) (2021)
- [DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation](https://mlsanity.com/paper/1904.08465/) (2019)
- [Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration](https://mlsanity.com/paper/2406.00123/) (2024)
- [Residual Aligner Network](https://mlsanity.com/paper/2203.04290/) (2022)
- [SAME++: A Self-supervised Anatomical eMbeddings Enhanced medical image registration framework using stable sampling and regularized transformation](https://mlsanity.com/paper/2311.14986/) (2023)

## Abstract (arXiv)

Deformable image registration is a fundamental task in medical image processing. Traditional optimization-based methods often struggle with accuracy in dealing with complex deformation. Recently, learning-based methods have achieved good performance on public datasets, but the scarcity of medical image data makes it challenging to build a generalizable model to handle diverse real-world scenarios. To address this, we propose a training-data-free learning-based method, Neural Correspondence Field (NCF), which can learn from just one data pair. Our approach employs a compact neural network to model the correspondence field and optimize model parameters for each individual image pair. Consequently, each pair has a unique set of network weights. Notably, our model is highly efficient, utilizing only 0.06 million parameters. Evaluation results showed that the proposed method achieved superior performance on a public Lung CT dataset and outperformed a traditional method on a head and neck dataset, demonstrating both its effectiveness and efficiency.