Neural Diffusion PDEs, Differential Geometry, and Graph Neural Networks.
Michael M. BronsteinPublished in: IMPROVE (2022)
Keyphrases
- differential geometry
- neural network
- structure tensor
- anisotropic diffusion
- nonlinear diffusion
- diffusion process
- partial differential equations
- diffusion equation
- infinite dimensional
- image denoising
- level set
- optical flow
- feed forward
- numerical solution
- denoising
- tensor field
- riemannian manifolds
- edge detection
- noise removal
- scale spaces
- shape space
- human vision
- diffusion tensor
- multiscale
- image processing