Neural Nano-Optics for High-quality Thin Lens Imaging

TL;DR

This paper introduces neural nano-optics, a novel approach combining differentiable learning of metasurface structures with neural image reconstruction, achieving high-quality, wide field-of-view nano-imaging with significantly reduced error.

Contribution

It presents the first neural nano-optics method that optimizes metasurface design and image reconstruction jointly, surpassing previous image quality limitations.

Findings

Achieved an order of magnitude lower reconstruction error.

Demonstrated a high-quality nano-imager with a 0.5 mm, f/2 aperture.

Enabled the widest field of view for full-color metasurface imaging.

Abstract

Nano-optic imagers that modulate light at sub-wavelength scales could unlock unprecedented applications in diverse domains ranging from robotics to medicine. Although metasurface optics offer a path to such ultra-small imagers, existing methods have achieved image quality far worse than bulky refractive alternatives, fundamentally limited by aberrations at large apertures and low f-numbers. In this work, we close this performance gap by presenting the first neural nano-optics. We devise a fully differentiable learning method that learns a metasurface physical structure in conjunction with a novel, neural feature-based image reconstruction algorithm. Experimentally validating the proposed method, we achieve an order of magnitude lower reconstruction error. As such, we present the first high-quality, nano-optic imager that combines the widest field of view for full-color metasurface operation while simultaneously achieving the largest demonstrated 0.5 mm, f/2 aperture.