# Learning a Generative Motion Model from Image Sequences based on a Latent Motion Matrix

arXiv: https://arxiv.org/abs/2011.01741 · HTML: https://mlsanity.com/paper/2011.01741/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 6 of 6)

- [Generative Myocardial Motion Tracking via Latent Space Exploration with Biomechanics-informed Prior](https://mlsanity.com/paper/2206.03830/) (2022)
- [CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy](https://mlsanity.com/paper/2301.13098/) (2023)
- [TLRN: Temporal Latent Residual Networks For Large Deformation Image Registration](https://mlsanity.com/paper/2407.11219/) (2024)
- [3D Brain and Heart Volume Generative Models: A Survey](https://mlsanity.com/paper/2210.05952/) (2022)
- [Unsupervised dynamic modeling of medical image transformation](https://mlsanity.com/paper/2103.00930/) (2021)
- [Online learning in motion modeling for intra-interventional image sequences](https://mlsanity.com/paper/2410.11491/) (2024)

## Abstract (arXiv)

We propose to learn a probabilistic motion model from a sequence of images for spatio-temporal registration. Our model encodes motion in a low-dimensional probabilistic space - the motion matrix - which enables various motion analysis tasks such as simulation and interpolation of realistic motion patterns allowing for faster data acquisition and data augmentation. More precisely, the motion matrix allows to transport the recovered motion from one subject to another simulating for example a pathological motion in a healthy subject without the need for inter-subject registration. The method is based on a conditional latent variable model that is trained using amortized variational inference. This unsupervised generative model follows a novel multivariate Gaussian process prior and is applied within a temporal convolutional network which leads to a diffeomorphic motion model. Temporal consistency and generalizability is further improved by applying a temporal dropout training scheme. Applied to cardiac cine-MRI sequences, we show improved registration accuracy and spatio-temporally smoother deformations compared to three state-of-the-art registration algorithms. Besides, we demonstrate the model's applicability for motion analysis, simulation and super-resolution by an improved motion reconstruction from sequences with missing frames compared to linear and cubic interpolation.