Litcius/Paper detail

Deep-learning-driven end-to-end metalens imaging

Joonhyuk Seo, Jaegang Jo, Joohoon Kim, J.S. Kang, Chanik Kang, Seong‐Won Moon, Eunji Lee, Jehyeong Hong, Junsuk Rho, Hsiao L. Chung

2024Advanced Photonics91 citationsDOIOpen Access PDF

Abstract

Recent advances in metasurface lenses (metalenses) have shown great potential for opening a new era in compact imaging, photography, light detection, and ranging (LiDAR) and virtual reality/augmented reality applications. However, the fundamental trade-off between broadband focusing efficiency and operating bandwidth limits the performance of broadband metalenses, resulting in chromatic aberration, angular aberration, and a relatively low efficiency. A deep-learning-based image restoration framework is proposed to overcome these limitations and realize end-to-end metalens imaging, thereby achieving aberration-free full-color imaging for mass-produced metalenses with 10 mm diameter. Neural-network-assisted metalens imaging achieved a high resolution comparable to that of the ground truth image.

Topics & Concepts

End-to-end principleComputer scienceArtificial intelligenceElectron and X-Ray Spectroscopy TechniquesNon-Destructive Testing TechniquesIntegrated Circuits and Semiconductor Failure Analysis