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

IY Chun, Z Huang, H Lim… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
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 …

Improved low-count quantitative PET reconstruction with an iterative neural network

H Lim, IY Chun, YK Dewaraja… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
Image reconstruction in low-count PET is particularly challenging because gammas from
natural radioactivity in Lu-based crystals cause high random fractions that lower the …

Convolutional analysis operator learning: Acceleration and convergence

IY Chun, JA Fessler - IEEE Transactions on Image Processing, 2019 - ieeexplore.ieee.org
Convolutional operator learning is gaining attention in many signal processing and
computer vision applications. Learning kernels has mostly relied on so-called patch-domain …

Accelerated Log-Regularized Convolutional Transform Learning and Its Convergence Guarantee

Z Li, H Zhao, Y Guo, Z Yang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Convolutional transform learning (CTL), learning filters by minimizing the data fidelity loss
function in an unsupervised way, is becoming very pervasive, resulting from kee** the …

Convolutional analysis operator learning for multifocus image fusion

C Zhang, Z Feng - Signal Processing: Image Communication, 2022 - Elsevier
Sparse representation (SR), convolutional sparse representation (CSR) and convolutional
dictionary learning (CDL) are synthetic-based priors that have proven to be successful in …

Learning deep analysis dictionaries for image super-resolution

JJ Huang, PL Dragotti - IEEE Transactions on Signal …, 2020 - ieeexplore.ieee.org
Inspired by the recent success of deep neural networks and the recent efforts to develop
multi-layer dictionary models, we propose a Deep Analysis dictionary Model (DeepAM) …