$\texttt{NePhi}$: Neural Deformation Fields for Approximately Diffeomorphic Medical Image Registration

arXiv:2309.07322v2 Announce Type: replace
Abstract: This work proposes NePhi, a generalizable neural deformation model which results in approximately diffeomorphic transformations. In contrast to the predominant voxel-based transformation fields used in learning-based registration approaches, NePhi represents deformations functionally, leading to great flexibility within the design space of memory consumption during training and inference, inference time, registration accuracy, as well as transformation regularity. Specifically, NePhi 1) requires less memory compared to voxel-based learning approaches, 2) improves inference speed by predicting latent codes, …

abstract arxiv consumption contrast cs.cv design fields flexibility image medical memory memory consumption registration results space training transformation type voxel work