Back to Search Start Over

Efficient and accurate inversion of multiple scattering with deep learning.

Authors :
Sun Y
Xia Z
Kamilov US
Source :
Optics express [Opt Express] 2018 May 28; Vol. 26 (11), pp. 14678-14688.
Publication Year :
2018

Abstract

Image reconstruction under multiple light scattering is crucial in a number of applications such as diffraction tomography. The reconstruction problem is often formulated as a nonconvex optimization, where a nonlinear measurement model is used to account for multiple scattering and regularization is used to enforce prior constraints on the object. In this paper, we propose a powerful alternative to this optimization-based view of image reconstruction by designing and training a deep convolutional neural network that can invert multiple scattered measurements to produce a high-quality image of the refractive index. Our results on both simulated and experimental datasets show that the proposed approach is substantially faster and achieves higher imaging quality compared to the state-of-the-art methods based on optimization.

Details

Language :
English
ISSN :
1094-4087
Volume :
26
Issue :
11
Database :
MEDLINE
Journal :
Optics express
Publication Type :
Academic Journal
Accession number :
29877404
Full Text :
https://doi.org/10.1364/OE.26.014678