To this end, we solve the linear inverse problem of undersampled MRI reconstruction in a variational setting.
We propose a novel learning-based framework for image reconstruction particularly designed for training without ground truth data, which has three major building blocks: energy-based learning, a patch-based Wasserstein loss functional, and shared prior learning.
In this work, we combine the variational formulation of inverse problems with deep learning by introducing the data-driven general-purpose total deep variation regularizer.
Diverse inverse problems in imaging can be cast as variational problems composed of a task-specific data fidelity term and a regularization term.
We investigate a well-known phenomenon of variational approaches in image processing, where typically the best image quality is achieved when the gradient flow process is stopped before converging to a stationary point.