Reality-Infused Deep Learning for Angle-resolved Quasi-optical Fourier Surfaces

TL;DR

This paper introduces a deep learning framework that leverages real-world measurements to accurately and rapidly predict angular dispersion in optical Fourier surfaces, overcoming limitations of traditional simulation methods.

Contribution

It presents a novel reality-infused deep learning approach that incorporates fabrication and measurement imperfections for real-time prediction of OFS responses.

Findings

High predictive accuracy across broad angular and spectral ranges

Significant acceleration of the optical design process

Enhanced understanding of angle-resolved responses in OFSs

Abstract

Optical Fourier surfaces (OFSs), featuring sinusoidally profiled diffractive elements, manipulate light through patterned nanostructures and incident angle modulation. Compared to altering structural parameters, tuning elevation and azimuth angles offers greater design flexibility for light field control. However, angle-resolved responses of OFSs are often complex due to diverse mode excitations and couplings, complicating the alignment between simulations and practical fabrication. Here, we present a reality-infused deep learning framework, empowered by angle-resolved measurements, to enable real-time and accurate predictions of angular dispersion in quasi-OFSs. This approach captures critical features, including nanofabrication and measurement imperfections, which conventional simulation-based methods typically overlook. Our framework significantly accelerates the design process while achieving predictive performance highly consistent with experimental observations across broad angular and spectral ranges. Our study supports valuable insights into the development of OFS-based devices, and represents a paradigm shift from simulation-driven to reality-infused methods, paving the way for advancements in optical design applications.