Fetching the paper…

Reading the bibliography…

2018

Off-the-grid model based deep learning (O-MODL)

Pramanik, Aniket, Aggarwal, Hemant Kumar, Jacob, Mathews

Original
PDF
Post on X

Understand

We introduce a model based off-the-grid image reconstruction algorithm using deep learned priors.

The main difference of the proposed scheme with current deep learning strategies is the learning of non-linear annihilation relations in Fourier space.
We rely on a model based framework, which allows us to use a significantly smaller deep network, compared to direct approaches that also learn how to invert the forward model.
Preliminary comparisons against image domain MoDL approach demonstrates the potential of the off-the-grid formulation.

Off-the-grid model based deep learning (O-MODL) · Around

Built on

“Low-rank modeling of local k k -space neighborhoods (loraks) for constrained mri,”
Justin P Haldar, · 2014
Earlier work this paper cites.
“Off-the-Grid Recovery of Piecewise Constant Images from Few Fourier Samples,”
Greg Ongie and Mathews Jacob, · 2016
Earlier work this paper cites.

Similar

“Deep Convolutional Neural Network for Inverse Problems in Imaging,”
Kyong Hwan Jin, Michael T. McCann, Emmanuel Froustey, and Michael Unser, · 2017
Cited alongside, same era.
“Modl: Model based deep learning architecture for inverse problems,”
Original
Hemant Kumar Aggarwal, Merry P Mani, and Mathews Jacob, · 2017
Cited alongside, same era.

Then

“Deep convolutional framelets: A general deep learning framework for inverse problems,”
Jong Chul Ye, Yoseob Han, and Eunju Cha, · 2018
Closest in time.
“k-space deep learning for accelerated mri,”
Original
Yoseob Han and Jong Chul Ye, · 2018
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…