Neural network assisted high-spatial-resolution polarimetry with non-interleaved chiral metasurfaces.

Polarimetry plays an indispensable role in modern optics. Nevertheless, the current strategies generally suffer from bulky system volume or spatial multiplexing scheme, resulting in limited performances when dealing with inhomogeneous polarizations. Here, we propose a non-interleaved, interferometric method to analyze the polarizations based on a tri-channel chiral metasurface. A deep convolutional neural network is also incorporated to enable fast, robust and accurate polarimetry. Spatially uniform and nonuniform polarizations are both measured through the metasurface experimentally. Distinction between two semblable glasses is also demonstrated. Our strategy features the merits of compactness and high spatial resolution, and would inspire more intriguing design for detecting and sensing.

Deep learning enhanced achromatic imaging with a singlet flat lens.

Correction of chromatic aberration is an important issue in color imaging and display. However, realizing broadband achromatic imaging by a singlet lens with high comprehensive performance still remains challenging, though many achromatic flat lenses have been reported recently. Here, we propose a deep-learning-enhanced singlet planar imaging system, implemented by a 3 mm-diameter achromatic flat lens, to achieve relatively high-quality achromatic imaging in the visible. By utilizing a multi-scale convolutional neural network (CNN) imposed to an achromatic multi-level diffractive lens (AMDL), the white light imaging qualities are significantly improved in both indoor and outdoor scenarios. Our experiments are fulfilled via a large paired imaging dataset with respect to a 3 mm-diameter AMDL, which guaranteed with achromatism in a broad wavelength range (400-1100 nm) but a relative low efficiency (∼45%). After our CNN enhancement, the imaging qualities are improved by ∼2 dB, showing competitive achromatic and high-quality imaging with a singlet lens for practical applications.