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 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 also introduce the negative Pearson correlation coefficient (NPCC) loss function for neural net training and show that the NPCC 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.

中文翻译：

---

使用密集连接的卷积网络通过玻璃扩散器成像

通过散射进行的计算成像通常是通过首先对散射介质进行表征，从而获得其正向算子，然后将正则化形式的附加先验强加于重建函数上来改善最初不适定的逆问题的条件。在函数中，必须明确或参数地输入正向运算符和正则化函数（例如，分别输入散射矩阵和字典）。但是，确定这些表示的过程通常不完整，容易出错或不可行。最近，有人提出了深度学习架构来通过示例学习正向运算符和正则化器。据我们所知，在这里，我们首次提出了建议，一种称为“ IDiffNet”的卷积神经网络体系结构，用于通过扩散介质成像的问题，并通过对经过良好校准的扩散器进行广泛的测试，证明了IDiffNet具有出色的泛化能力。我们还介绍了用于神经网络训练的负Pearson相关系数（NPCC）损失函数，并表明NPCC更适合于空间稀疏的对象和强散射条件。我们的结果表明，通过使用多个训练和测试对象数据库可以证明，卷积体系结构对于优先级选择具有鲁棒性，并且能够实现比以前报道的更高的空间带宽乘积重构。