Adversarial Sensing for Sub-Diffraction Imaging
Computational Optical Sensing and Imaging — 2022[paper]
We propose a self-supervised learning-based framework for reconstructing images from partially unknown and non-linear measurements. We apply our technique, which is based on matching the distributions of real and simulated observations, to long-range Fourier Ptychography.
@article{ Feng2022Adversarial,
author = { Feng, Brandon Y. and Metzler, Christopher A. },
title = { Adversarial Sensing for Sub-Diffraction Imaging },
journal = { Computational Optical Sensing and Imaging },
year = { 2022 },
}