Speeding up scaled gradient projection methods using deep neural networks for inverse problems in image processing

02/07/2019
by   Byung Hyun Lee, et al.
0

Conventional optimization based methods have utilized forward models with image priors to solve inverse problems in image processing. Recently, deep neural networks (DNN) have been investigated to significantly improve the image quality of the solution for inverse problems. Most DNN based inverse problems have focused on using data-driven image priors with massive amount of data. However, these methods often do not inherit nice properties of conventional approaches using theoretically well-grounded optimization algorithms such as monotone, global convergence. Here we investigate another possibility of using DNN for inverse problems in image processing. We propose methods to use DNNs to seamlessly speed up convergence rates of conventional optimization based methods. Our DNN-incorporated scaled gradient projection methods, without breaking theoretical properties, significantly improved convergence speed over state-of-the-art conventional optimization methods such as ISTA or FISTA in practice for inverse problems such as image inpainting, compressive image recovery with partial Fourier samples, image deblurring, and medical image reconstruction with sparse-view projections.

READ FULL TEXT

page 6

page 7

page 8

research
06/06/2020

Regularization of Inverse Problems by Neural Networks

Inverse problems arise in a variety of imaging applications including co...
research
11/24/2022

Deep unfolding as iterative regularization for imaging inverse problems

Recently, deep unfolding methods that guide the design of deep neural ne...
research
03/29/2017

One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models

While deep learning methods have achieved state-of-the-art performance i...
research
03/20/2023

Convergence Guarantees of Overparametrized Wide Deep Inverse Prior

Neural networks have become a prominent approach to solve inverse proble...
research
12/17/2019

Sampled Limited Memory Methods for Massive Linear Inverse Problems

In many modern imaging applications the desire to reconstruct high resol...
research
08/13/2014

Gradient Distribution Priors for Biomedical Image Processing

Ill-posed inverse problems are commonplace in biomedical image processin...
research
04/25/2022

Hybrid ISTA: Unfolding ISTA With Convergence Guarantees Using Free-Form Deep Neural Networks

It is promising to solve linear inverse problems by unfolding iterative ...

Please sign up or login with your details

Forgot password? Click here to reset