SrvfNet: A Generative Network for Unsupervised Multiple Diffeomorphic Shape Alignment

2021/04/27 by Elvis Nunez, Nunez, Elvis, Andrew Lizarraga +3
Computer Science · Mathematics · #Computer Vision and Pattern Recognition (cs.CV) #Differential Geometry (math.DG) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #cs.CV #cs.LG #math.DG

paper · pdf · doi:10.48550/arxiv.2104.13449

arxiv created 2021/04/27 · arxiv updated 2021/04/29

Abstract

We present SrvfNet, a generative deep learning framework for the joint multiple alignment of large collections of functional data comprising square-root velocity functions (SRVF) to their templates. Our proposed framework is fully unsupervised and is capable of aligning to a predefined template as well as jointly predicting an optimal template from data while simultaneously achieving alignment. Our network is constructed as a generative encoder-decoder architecture comprising fully-connected layers capable of producing a distribution space of the warping functions. We demonstrate the strength of our framework by validating it on synthetic data as well as diffusion profiles from magnetic resonance imaging (MRI) data.

Related

• DeepFRC: An End-to-End Deep Learning Model for Functional Registration and Classification
• Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment
• NimbleReg: A light-weight deep-learning framework for diffeomorphic image registration
• SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models
• Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow