Neumann Networks for Inverse Problems in Imaging

01/13/2019
by   Davis Gilton, et al.
0

Many challenging image processing tasks can be described by an ill-posed linear inverse problem: deblurring, deconvolution, inpainting, compressed sensing, and superresolution all lie in this framework. Traditional inverse problem solvers minimize a cost function consisting of a data-fit term, which measures how well an image matches the observations, and a regularizer, which reflects prior knowledge and promotes images with desirable properties like smoothness. Recent advances in machine learning and image processing have illustrated that it is often possible to learn a regularizer from training data that can outperform more traditional regularizers. We present an end-to-end, data-driven method of solving inverse problems inspired by the Neumann series, which we call a Neumann network. Rather than unroll an iterative optimization algorithm, we truncate a Neumann series which directly solves the linear inverse problem with a data-driven nonlinear regularizer. The Neumann network architecture outperforms traditional inverse problem solution methods, model-free deep learning approaches, and state-of-the-art unrolled iterative methods on standard datasets. Finally, when the images belong to a union of subspaces and under appropriate assumptions on the forward model, we prove there exists a Neumann network configuration that well-approximates the optimal oracle estimator for the inverse problem and demonstrate empirically that the trained Neumann network has the form predicted by theory.

READ FULL TEXT

page 19

page 20

page 21

page 22

page 23

page 24

page 25

research
06/05/2020

Joint learning of variational representations and solvers for inverse problems with partially-observed data

Designing appropriate variational regularization schemes is a crucial pa...
research
08/12/2023

A preconditioned Krylov subspace method for linear inverse problems with general-form Tikhonov regularization

Tikhonov regularization is a widely used technique in solving inverse pr...
research
06/15/2020

Total Deep Variation: A Stable Regularizer for Inverse Problems

Various problems in computer vision and medical imaging can be cast as i...
research
10/10/2022

Loop Unrolled Shallow Equilibrium Regularizer (LUSER) – A Memory-Efficient Inverse Problem Solver

In inverse problems we aim to reconstruct some underlying signal of inte...
research
01/08/2023

Deep Injective Prior for Inverse Scattering

In electromagnetic inverse scattering, we aim to reconstruct object perm...
research
07/30/2023

Deep Unrolling Networks with Recurrent Momentum Acceleration for Nonlinear Inverse Problems

Combining the strengths of model-based iterative algorithms and data-dri...
research
07/20/2022

Deep Preconditioners and their application to seismic wavefield processing

Seismic data processing heavily relies on the solution of physics-driven...

Please sign up or login with your details

Forgot password? Click here to reset