End-to-end metasurface inverse design for single-shot multi-channel imaging

TL;DR

This paper presents an end-to-end inverse design approach for metaoptics that enables single-shot multi-channel imaging, including depth, spectral, and polarization information, using a simple setup without complex optics or large training data.

Contribution

The authors develop a physically interpretable inverse design framework for metasurfaces that can reconstruct multi-channel information from a single monochrome image, avoiding neural networks and extensive training.

Findings

Achieved robust multi-channel reconstruction with less than 10% error.

Designed large-area metasurfaces compatible with standard lithography.

Demonstrated multi-spectral, depth-spectral, and spectro-polarimetric imaging capabilities.

Abstract

We introduce end-to-end metaoptics inverse design for multi-channel imaging: reconstruction of depth, spectral and polarization channels from a single-shot monochrome image. The proposed technique integrates a single-layer metasurface frontend with an efficient Tikhonov reconstruction backend, without any additional optics except a grayscale sensor. Our method yields multi-channel imaging by spontaneous demultiplexing: the metaoptics front-end separates different channels into distinct spatial domains whose locations on the sensor are optimally discovered by the inverse-design algorithm. We present large-area metasurface designs, compatible with standard lithography, for multi-spectral imaging, depth-spectral imaging, and ``all-in-one'' spectro-polarimetric-depth imaging with robust reconstruction performance ($\lesssim 10\%$ error with 1\% detector noise). In contrast to neural networks, our framework is physically interpretable and does not require large training sets. It can be used to reconstruct arbitrary three-dimensional scenes with full multi-wavelength spectra and polarization textures.