Abstract

This study uses a generative adversarial network to design multilevel optical anisotropic diffraction gratings with specific customizable characteristics. As input, this method uses the far electric field of polarization and intensity in each diffracted light through the gratings to design. Using the finite-difference time-domain method, the designed structures are numerically evaluated, confirming that they can be created with the intended parameters. Multilevel optical anisotropic diffraction gratings created this way can be used in various fields to develop improved optical elements.

© 2024 Optica Publishing Group

Multilevel anisotropic diffractive optical elements fabricated by means of stepping photo-alignment technique using photo-cross-linkable polymer liquid crystals

Kohei Noda, Kotaro Kawai, Tomoyuki Sasaki, Nobuhiro Kawatsuki, and Hiroshi Ono
Appl. Opt. 53(12) 2556-2561 (2014)

Unsupervised speckle denoising in digital holographic interferometry based on 4-f optical simulation integrated cycle-consistent generative adversarial network

HongBo Yu, Qiang Fang, QingHe Song, Silvio Montresor, Pascal Picart, and Haiting Xia
Appl. Opt. 63(13) 3557-3569 (2024)

Two-dimensional binary phase gratings for zero-order and high-order diffraction suppression

Yifan Chen, Kun Zhang, Xinjie Lv, Gang Zhao, and Shining Zhu
Appl. Opt. 63(9) 2286-2293 (2024)

Combination of near-infrared spectroscopy with Wasserstein generative adversarial networks for rapidly detecting raw material quality for formula products

Xiaowei Xin, Junhua Jia, Shunpeng Pang, Ruotong Hu, Huili Gong, Xiaoyan Gao, and Xiangqian Ding
Opt. Express 32(4) 5529-5549 (2024)

Influence of diffraction distance on image restoration in deep learning networks

Shihong Huang, Yanxu Yang, Jiayang Wu, and Caihou Lin
Appl. Opt. 63(9) 2306-2313 (2024)