Misalignment resilient phase-filtered diffractive deep neural networks

Diffractive deep neural networks (D²NN) have been widely applied as a novel method for wavefront shaping and beam manipulation. However, achieving high-precision alignment across multiple planes remains a significant challenge. In this paper, we propose a phase-filtered diffractive deep neural network (PF-D²NN), which introduces a phase filtering operator during phase optimization for the modulation layers to enhance the robustness of the network. A back-propagation (BP) algorithm is specifically designed for the phase optimization of the PF-D²NN. Both simulations and experiments validate that the proposed PF-D²NN is quite robust with respect to the alignment error. The experiment results show that even when conventional D²NN fail to produce clear images with the misalignment over 5 pixels, the proposed network continues to deliver clear images for various targets.