Two-dimensional optical differentiator for broadband edge detection based on dielectric metasurface.

Image edge processing has widespread adoption in a variety of scientific and industrial scenarios. To date, implementations of image edge processing have mostly been done electronically, but there are still difficulties to achieve real-time, high-throughput, and low power consumption image edge processing. The advantages of optical analog computing include low power consumption, fast transmission speed, and high parallel processing capability, and optical analog differentiators make this process possible. However, the proposed analog differentiators can hardly meet the requirements of broadband, polarization insensitive, high contrast, and high efficiency at the same time. Moreover, they are limited to one-dimensional differentiation or work in reflection mode. To be better compatible with two-dimensional image processing or image recognition systems, two-dimensional optical differentiators that integrate the above advantages are urgently needed. In this Letter, a two-dimensional analog optical differentiator with edge detection operating in transmission mode is proposed. It can cover the visible band, is polarization uncorrelated, and has a resolution that reaches 1.7 µm. The efficiency of the metasurface is higher than 88%.

Design of All-Dielectric Metasurface-Based Subtractive Color Filter by Artificial Neural Network.

Structural colors produced by light manipulating at subwavelength dimensions have been widely studied. In this work, a metasurface-based subtractive color filter (SCF) is demonstrated. The color display of the SCF is confirmed by finding the complementary color of colors filtered by SCF within the color wheel. In addition, two artificial neural network (ANN) models are utilized to accelerate the metasurface forward prediction, and the long short-term memory (LSTM) shows much better performance than traditional multilayer perceptron (MLP). Meanwhile, we train an inverse ANN model established with LSTM to recover the optimal geometric parameter combinations of the meta-atoms. With the variation of the geometric parameters of meta-atoms, versatile color displays of structural colors are realized. The metasurface we propose exhibits good performance of transmissive-type structural color in visible range. The work provides a method for high-efficiency geometric parameter prediction, and paves the way to nanostructure-based color design for display and anticounterfeiting applications.

Long short-term memory neural network for directly inverse design of nanofin metasurface.

In this Letter, the neural network long short-term memory (LSTM) is used to quickly and accurately predict the polarization sensitivity of a nanofin metasurface. In the forward prediction, we construct a deep neural network (DNN) with the same structure for comparison with LSTM. The test results show that LSTM has a higher accuracy and better robustness than DNN in similar cases. In the inverse design, we directly build an LSTM to reverse the design similar to the forward prediction network. By inputting the extinction ratio value in 8-12 µm, the inverse network can directly provide the unit cell geometry of the nanofin metasurface. Compared with other methods used to inverse design photonic structures using deep learning, our method is more direct because no other networks are introduced.