{"ID":2850803,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.21924","arxiv_id":"2510.21924","title":"Inverse Design of Metasurface for Spectral Imaging","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.","short_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...","url_abs":"https://arxiv.org/abs/2510.21924","url_pdf":"https://arxiv.org/pdf/2510.21924v1","authors":"[\"Rongzhou Chen\",\"Haitao Nie\",\"Shuo Zhu\",\"Yaping Zhao\",\"Chutian Wang\",\"Edmund Y. Lam\"]","published":"2025-10-24T18:00:06Z","proceeding":"eess.IV","tasks":"[\"eess.IV\"]","methods":"[]","has_code":false}