Inverse Design of Metasurface for Spectral Imaging

TL;DR

This paper presents a physics-data co-driven inverse design framework for reconfigurable metasurfaces using a neural simulator, enabling compact spectral imaging with improved fidelity and noise resilience.

Contribution

It introduces a differentiable neural simulator and a joint optimization approach for metasurface design and spectral decoding in hyperspectral imaging.

Findings

Achieved up to 7.6 dB improvement in reconstruction SNR.

Enhanced noise resilience and measurement matrix conditioning.

Demonstrated effective spectral imaging in the shortwave infrared region.

Abstract

Inverse design of metasurfaces for the joint optimization of optical modulation and algorithmic decoding in computational optics presents significant challenges, especially in applications such as hyperspectral imaging. We introduce a physics-data co-driven framework for designing reconfigurable metasurfaces fabricated from the phase-change material Ge2Sb2Se4Te1 to achieve compact, compressive spectral imaging in the shortwave infrared region. Central to our approach is a differentiable neural simulator, trained on over 320,000 simulated geometries, that accurately predicts spectral responses across 11 crystallization states. This differentiability enables end-to-end joint optimization of the metasurface geometry, its spectral encoding function, and a deep reconstruction network. We also propose a soft shape regularization technique that preserves manufacturability during gradient-based updates. Experiments show that our optimized system improves reconstruction fidelity by up to 7.6 dB in the peak-signal-to-noise ratio, with enhanced noise resilience and improved measurement matrix conditioning, underscoring the potential of our approach for high-performance hyperspectral imaging.