# SrvfNet: A Generative Network for Unsupervised Multiple Diffeomorphic Shape Alignment

arXiv: https://arxiv.org/abs/2104.13449 · HTML: https://mlsanity.com/paper/2104.13449/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 27 Apr 2021.

## Builds on (most cited first, 5 of 5)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping](https://mlsanity.com/paper/1906.05947/) (2019)
- [Autowarp: Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders](https://mlsanity.com/paper/1810.10107/) (2018)
- [Learning to Exploit Invariances in Clinical Time-Series Data using Sequence Transformer Networks](https://mlsanity.com/paper/1808.06725/) (2018)
- [Gaussian Process Latent Variable Alignment Learning](https://mlsanity.com/paper/1803.02603/) (2018)

## Built on by (most cited first, 1 of 1)

- [Closed-Form Diffeomorphic Transformations for Time Series Alignment](https://mlsanity.com/paper/2206.08107/) (2022)

## Abstract (arXiv)

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.