Unsupervised deep learning methods for biological image reconstruction and enhancement: An overview from a signal processing perspective

M Akçakaya, B Yaman, H Chung… - IEEE Signal Processing …, 2022 - ieeexplore.ieee.org
Recently, deep learning (DL) approaches have become the main research frontier for
biological image reconstruction and enhancement problems thanks to their high …

A review of deep learning methods for compressed sensing image reconstruction and its medical applications

Y **e, Q Li - Electronics, 2022 - mdpi.com
Compressed sensing (CS) and its medical applications are active areas of research. In this
paper, we review recent works using deep learning method to solve CS problem for images …

RARE: Image reconstruction using deep priors learned without groundtruth

J Liu, Y Sun, C Eldeniz, W Gan, H An… - IEEE Journal of …, 2020 - ieeexplore.ieee.org
Regularization by denoising (RED) is an image reconstruction framework that uses an
image denoiser as a prior. Recent work has shown the state-of-the-art performance of RED …

Physics-based learned design: optimized coded-illumination for quantitative phase imaging

MR Kellman, E Bostan, NA Repina… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Coded illumination can enable quantitative phase microscopy of transparent samples with
minimal hardware requirements. Intensity images are captured with different source …

Dense recurrent neural networks for accelerated MRI: History-cognizant unrolling of optimization algorithms

SAH Hosseini, B Yaman, S Moeller… - IEEE Journal of …, 2020 - ieeexplore.ieee.org
Inverse problems for accelerated MRI typically incorporate domain-specific knowledge
about the forward encoding operator in a regularized reconstruction framework. Recently …

Sgd-net: Efficient model-based deep learning with theoretical guarantees

J Liu, Y Sun, W Gan, X Xu, B Wohlberg… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Deep unfolding networks have recently gained popularity for solving imaging inverse
problems. However, the computational and memory complexity of data-consistency layers …

Solving phase retrieval with a learned reference

R Hyder, Z Cai, MS Asif - European Conference on Computer Vision, 2020 - Springer
Fourier phase retrieval is a classical problem that deals with the recovery of an image from
the amplitude measurements of its Fourier coefficients. Conventional methods solve this …

Positive sparse signal denoising: What does a cnn learn?

AH Al-Shabili, I Selesnick - IEEE Signal Processing Letters, 2022 - ieeexplore.ieee.org
Convolutional neural networks (CNNs) provide impressive empirical success in various
tasks; however, their inner workings generally lack interpretability. In this paper, we interpret …

Learned patch-based regularization for inverse problems in imaging

D Gilton, G Ongie, R Willett - 2019 ieee 8th international …, 2019 - ieeexplore.ieee.org
Many modern approaches to image reconstruction are based on learning a regularizer that
implicitly encodes a prior over the space of images. For large-scale images common in …

Data-driven computational imaging for scientific discovery

A Olsen, Y Hu, V Ganapati - arxiv preprint arxiv:2210.16709, 2022 - arxiv.org
In computational imaging, hardware for signal sampling and software for object
reconstruction are designed in tandem for improved capability. Examples of such systems …