Nonlinear motion separation via untrained generator networks with disentangled latent space variables and applications to cardiac MRI.
AbdullahMartin HollerKarl KunischMalena Sabate LandmanPublished in: CoRR (2022)
Keyphrases
- gaussian process latent variable models
- latent space
- cardiac mri
- low dimensional
- high dimensional
- latent variables
- image sequences
- physiological parameters
- lower dimensional
- optical flow
- manifold learning
- data sets
- parameter space
- motion analysis
- dimensionality reduction
- gaussian process
- random variables
- feature space
- motion field
- motion model
- human motion
- motion segmentation
- left ventricle
- motion estimation
- motion tracking
- distance metric
- generative model
- matrix factorization
- gaussian processes
- probabilistic model
- left ventricular