High Efficiency Visible Achromatic Metalens Design via Deep Learning

Abstract

Metalenses with both achromatic performance and high focusing efficiency are always challenging, especially in visible range. In this work, a deep learning model is developed to accelerate the design of achromatic metalenses based on the geometric phase theory. During the building process of the phase response library and selection of the nano‐structures, converted transmission coefficients including both phase and amplitude are considered in order to ensure the achromatic focusing, as well as a high focusing efficiency. To test the performance of the design developed from the deep learning model, numerical simulations are performed in the visible wavelengths from 428 to 652 nm, which show a focal length of 266 µm with the deviation under 5%, and the average focusing efficiency reaches 52%.

Intelligent Phase Contrast Meta-Microscope System

“…In recent years, deep neural network-based (DNN) approaches have shown their remarkable ability to assist with a wide range of biomedical imaging tasks, such as object detection, cell segmentation, and image-to-image translations. − Via combination of optics and deep learning (DL) imaging algorithms, it is possible to enhance the quality and accuracy of images while simultaneously reducing the system complexity of optical microscopes and minimizing processing times. − Moreover, DNNs have recently been used to solve the challenges of metasurfaces, covering areas from fundamental unit cell design to a variety of imaging enhancements such as chromatic aberration correction, noise suppression, and contrast loss compensation. − The remarkable results of DNNs suggest that these approaches may become increasingly common in the development of innovative imaging solutions in the years to come.…”