DeepAI AI Chat
Log In Sign Up

Momentum-Net: Fast and convergent iterative neural network for inverse problems

by   Il Yong Chun, et al.

Iterative neural networks (INN) are rapidly gaining attention for solving inverse problems in imaging, image processing, and computer vision. INNs combine regression NNs and an iterative model-based image reconstruction (MBIR) algorithm, leading to both good generalization capability and outperforming reconstruction quality over existing MBIR optimization models. This paper proposes the first fast and convergent INN architecture, Momentum-Net, by generalizing a block-wise MBIR algorithm that uses momentums and majorizers with regression NNs. For fast MBIR, Momentum-Net uses momentum terms in extrapolation modules, and noniterative MBIR modules at each layer by using majorizers, where each layer of Momentum-Net consists of three core modules: image refining, extrapolation, and MBIR. Momentum-Net guarantees convergence to a fixed-point for general differentiable (non)convex MBIR functions (or data-fit terms) and convex feasible sets, under two asymptomatic conditions. To consider data-fit variations across training and testing samples, we also propose a regularization parameter selection scheme based on the spectral radius of majorization matrices. Numerical experiments for light-field photography using a focal stack and sparse-view computational tomography demonstrate that given identical regression NN architectures, Momentum-Net significantly improves MBIR speed and accuracy over several existing INNs; it significantly improves reconstruction quality compared to a state-of-the-art MBIR method in each application.


page 12

page 13


Momentum-Net for Low-Dose CT Image Reconstruction

This paper applies the recent fast iterative neural network framework, M...

BCD-Net for Low-dose CT Reconstruction: Acceleration, Convergence, and Generalization

Obtaining accurate and reliable images from low-dose computed tomography...

An Improved Iterative Neural Network for High-Quality Image-Domain Material Decomposition in Dual-Energy CT

Dual-energy computed tomography (DECT) has been widely used in many appl...

Convolutional Analysis Operator Learning: Acceleration, Convergence, Application, and Neural Networks

Convolutional operator learning is increasingly gaining attention in man...

QISTA-Net: DNN Architecture to Solve ℓ_q-norm Minimization Problem and Image Compressed Sensing

In this paper, we reformulate the non-convex ℓ_q-norm minimization probl...

Fast Convex Pruning of Deep Neural Networks

We develop a fast, tractable technique called Net-Trim for simplifying a...