Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems.
Yingzhi XiaNicholas ZabarasPublished in: J. Comput. Phys. (2022)
Keyphrases
- generative model
- inverse problems
- multiscale
- high dimensional
- probabilistic model
- image reconstruction
- bayesian framework
- em algorithm
- partial differential equations
- global optimization
- image processing
- maximum likelihood
- prior knowledge
- semi supervised
- optimization methods
- convex optimization
- topic models
- edge detection
- natural images
- image representation
- feature selection
- image segmentation
- parameter space
- bayesian networks
- object recognition
- evolutionary algorithm
- missing data
- multi objective
- wavelet transform
- optimization problems
- dimensionality reduction
- higher order
- input image