Simultaneous boundary shape estimation and velocity field de-noising in Magnetic Resonance Velocimetry using Physics-informed Neural Networks.
Ushnish SenguptaAlexandros KontogiannisMatthew P. JuniperPublished in: CoRR (2021)
Keyphrases
- magnetic resonance
- shape estimation
- velocity field
- neural network
- denoising
- mr images
- medical images
- vector field
- optical flow
- shape from shading
- image registration
- flow field
- perspective projection
- image data
- image sequences
- rigid motion
- motion field
- pattern recognition
- image denoising
- computational fluid dynamics
- structure from motion
- object boundaries
- magnetic resonance images
- medical image analysis
- potential functions
- computer vision
- deformable models
- single image
- gray level
- least squares
- motion estimation
- pairwise
- computational complexity
- image processing
- machine learning