Inverse design of ultracompact multi-focal optical devices by diffractive neural networks

TL;DR

This paper introduces a deep learning-based inverse design method for creating ultracompact, multifunctional diffractive optical devices capable of multi-wavelength focusing and super-oscillatory spots, surpassing traditional single-lens limits.

Contribution

The authors develop adaptive deep diffractive neural networks (a-D$^2$NNs) for designing two-layer diffractive devices with enhanced multi-spectral focusing and super-oscillatory capabilities.

Findings

Achieved targeted spectral lineshapes and spatial PSFs with high efficiency.

Controlled spectral bandwidths at separate focal points beyond single-lens limits.

Demonstrated super-oscillatory focal spots at desired wavelengths.

Abstract

We propose an efficient inverse design approach for multifunctional optical elements based on adaptive deep diffractive neural networks (a-D$^2$NNs). Specifically, we introduce a-D$^2$NNs and design two-layer diffractive devices that can selectively focus incident radiation over two well-separated spectral bands at desired distances. We investigate focusing efficiencies at two wavelengths and achieve targeted spectral lineshapes and spatial point-spread functions (PSFs) with optimal focusing efficiency. In particular, we demonstrate control of the spectral bandwidths at separate focal positions beyond the theoretical limit of single-lens devices with the same aperture size. Finally, we demonstrate devices that produce super-oscillatory focal spots at desired wavelengths. The proposed method is compatible with current diffractive optics and doublet metasurface technology for ultracompact multispectral imaging and lensless microscopy applications.