Learning-based techniques have significantly improved the accuracy and speed of deformable image registration. However, challenges such as reducing computational complexity and handling large deformations persist. To address these challenges, we analyze how convolutional neural networks (ConvNets) influence registration performance using the Horn-Schunck optical flow equation. Supported by prior studies and our empirical experiments, we observe that ConvNets play two key roles in registration: linearizing local intensities and harmonizing global contrast variations. Based on these insights, we propose the Encoder-Only Image Registration (EOIR) framework, designed to achieve a better accuracy-efficiency trade-off. EOIR separates feature learning from flow estimation, employing only a 3-layer ConvNet for feature extraction and a set of 3-layer flow estimators to construct a Laplacian feature pyramid, progressively composing diffeomorphic deformations under a large-deformation model. Results on five datasets across different modalities and anatomical regions demonstrate EOIR's effectiveness, achieving superior accuracy-efficiency and accuracy-smoothness trade-offs. With comparable accuracy, EOIR provides better efficiency and smoothness, and vice versa. The source code of EOIR is publicly available on https://github.com/XiangChen1994/EOIR.

翻译：基于学习的技术显著提升了可变形图像配准的精度与速度。然而，降低计算复杂度与处理大形变等挑战依然存在。为应对这些挑战，我们利用Horn-Schunck光流方程分析了卷积神经网络（ConvNets）如何影响配准性能。基于先前研究及我们的实证实验，我们观察到ConvNets在配准中发挥两个关键作用：线性化局部强度与协调全局对比度变化。基于这些发现，我们提出了仅编码器图像配准（EOIR）框架，旨在实现更优的精度-效率权衡。EOIR将特征学习与流估计分离，仅采用一个3层ConvNet进行特征提取，并利用一组3层流估计器构建拉普拉斯特征金字塔，在大形变模型下逐步合成微分同胚形变。在涵盖不同模态与解剖区域的五个数据集上的结果表明，EOIR实现了卓越的精度-效率与精度-平滑度权衡。在精度相当的情况下，EOIR提供更优的效率与平滑度，反之亦然。EOIR的源代码已公开于https://github.com/XiangChen1994/EOIR。