SrvfNet: A Generative Network for Unsupervised Multiple Diffeomorphic Shape Alignment
This work addresses shape alignment challenges in fields like medical imaging, but it appears incremental as it builds on existing SRVF methods with a new network architecture.
The authors tackled the problem of unsupervised multiple diffeomorphic shape alignment by developing SrvfNet, a generative deep learning framework that jointly aligns large collections of functional data to templates, achieving alignment and template prediction simultaneously.
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.