Imaging through glass diffusers using densely connected convolutional networks

TL;DR

This paper introduces IDiffNet, a convolutional neural network designed for imaging through diffuse media, demonstrating superior generalization and higher resolution reconstructions compared to existing methods, especially under challenging scattering conditions.

Contribution

The paper presents the novel IDiffNet architecture that learns the forward operator and regularizer directly from data, improving imaging through scattering media without explicit medium characterization.

Findings

IDiffNet outperforms previous methods in space-bandwidth product.

Negative Pearson Correlation Coefficient loss enhances sparse object reconstruction.

Model generalizes well across different diffusers and object databases.

Abstract

Computational imaging through scatter generally is accomplished by first characterizing the scattering medium so that its forward operator is obtained; and then imposing additional priors in the form of regularizers on the reconstruction functional so as to improve the condition of the originally ill-posed inverse problem. In the functional, the forward operator and regularizer must be entered explicitly or parametrically (e.g. scattering matrices and dictionaries, respectively.) However, the process of determining these representations is often incomplete, prone to errors, or infeasible. Recently, deep learning architectures have been proposed to instead learn both the forward operator and regularizer through examples. Here, we propose for the first time, to our knowledge, a convolutional neural network architecture called "IDiffNet" for the problem of imaging through diffuse media and demonstrate that IDiffNet has superior generalization capability through extensive tests with well-calibrated diffusers. We found that the Negative Pearson Correlation Coefficient loss function for training is more appropriate for spatially sparse objects and strong scattering conditions. Our results show that the convolutional architecture is robust to the choice of prior, as demonstrated by the use of multiple training and testing object databases, and capable of achieving higher space-bandwidth product reconstructions than previously reported.