Skarsoulis, KyriakosKakkava, EiriniPsaltis, Demetri2021-05-182021-05-182021-05-182021-03-2610.1016/j.optcom.2021.126968https://infoscience.epfl.ch/handle/20.500.14299/178055Deep neural networks (DNNs) are used to reconstruct transmission speckle intensity patterns from the respective reflection speckle intensity patterns generated by illuminated parafilm layers. The dependence of the reconstruction accuracy on the thickness of the sample is examined for different illumination patterns of various feature sizes. High reconstruction accuracy is obtained even for large parafilm thicknesses, for which the memory effect of the sample is vanishingly small. The generalization capability of the DNN is also studied for unseen scatterers of the same type.Computational imagingScatteringSpeckle patternDeep neural networkMemory effectTransfer learningtext::journal::journal article::research article