Speckle suppression using F-D2NN in holographic display

Abstract

We propose a speckle suppression method using Fourier-domain diffraction deep neural networks (F-D2NN) in the holographic display. To the best of our knowledge, it is the first time that F-D2NN is applied for the holographic display quality enhancement. Unlike existing speckle suppression algorithms in the hologram generation, our proposed method works after the hologram reconstruction and improves the reconstructed quality independently of the hologram generation algorithm. The proposed method not only can alone suppress speckle noise generated by different holographic generation algorithms but also is effective to improve reconstruction quality further by jointing with other traditional speckle suppression algorithms. The proposed method provides a new approach for the quality enhancement of the holographic display.