Deep Learning Ghost Polarimetry of Two-Dimensional Objects with Amplitude Anisotropy

Abstract

This paper discusses the potential of deep learning in solving the inverse problem of computational ghost polarimetry. For the first time, it is demonstrated that the spatial distribution of the polarization properties of objects with linear amplitude anisotropy can be restored using a neural network trained on model data. The spatial distribution of the parameters of linear amplitude anisotropy is determined with an accuracy of 7.8\(\%\) and 15.6\(\%\) for the azimuth and the value of anisotropy, respectively.