Code

Deep Equilibrium Models for Solving Inverse Problems in Imaging

Extension of the deep equilibrium framework to solve linear inverse problems in computational imaging.
Code

Neumann Networks for Solving Linear Inverse Problems in Imaging

Neumann networks are a neural network meta-architecture that can be trained to solve linear inverse problems arising in computational imaging.
Link to Project Page Page
Code

Matrix Completion with Algebraic Variety Models

An extension of low-rank matrix completion to the case where the data lies on a low-dimensional algebraic variety. This includes data belonging to a union of low-dimensional subspaces, and other low-dimensional algebraic curves and surfaces.
Variety Matrix Completion (VMC) Code
Low Algebraic Dimension Matrix Completion (LADMC) Code

GIRAF algorithm for convolutional structured low-rank matrix completion problems

A fast algorithm for solving low-rank matrix completion problems with additional (block)-Toeplitz or (block)-Hankel structure, with application to undersampled MRI reconstruction.
Code

Super-resolution MRI using Off-the-Grid Compressive Imaging

An extension of the finite-rate-of-innovation (FRI) framework to a class of multi-dimensional piecewise smooth image models.
Code

Higher Degree Total Variation

An efficient extension of the total variation regularization penalty to higher order derivatives for use in inverse problems in imaging.
Link to CBIG Project Page
Code

Patch-based Non-Local Shrinkage

An algorithm for MRI reconstruction that utilizes a patch-based similarity prior.
Link to CBIG Project Page