Work

Misalignment resilient phase-filtered diffractive deep neural networks

Year: 2025

Type: article

Abstract: Diffractive deep neural networks (D 2 NN) 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-D 2 NN), 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-D 2 NN. Both simulations and experiments validate that the proposed PF-D 2 NN is quite robust with respect to the alignment error. The experiment results show that even when conventional D 2 NN fail to produce clear images with the misalignment over 5 pixels, the proposed network continues to deliver clear images for various targets.

Source: Optics Express

DOI: 10.1364/oe.558279

Authors: Ruotong Wang, Junhe Zhou

Language: English

Topic: Neural Networks and Reservoir Computing

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,270

Funders: National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality

Awards: G8200072349, G897182718