Ghost imaging based on Y-net: a dynamic coding and decoding approach.

Ghost imaging incorporating deep learning technology has recently attracted much attention in the optical imaging field. However, deterministic illumination and multiple exposure are still essential in most scenarios. Here we propose a ghost imaging scheme based on a novel dynamic decoding deep learning framework (Y-net), which works well under both deterministic and indeterministic illumination.

Non-locally coded Fourier-transform ghost imaging.

A non-locally coded Fourier-transform ghost imaging (FGI) scheme and relevant coded phase retrieval method have been proposed to improve the image quality in ghost imaging. By inserting masks in the reference beam, the sample in the test beam is non-locally modulated, and coded Fourier-transform diffraction patterns of the sample are obtained via intensity correlation calculations between the two beams. Encoding and decoding procedures are incorporated in the phase retrieval process based on traditional hybrid input-output algorithm.

Spatial multiplexing reconstruction for Fourier-transform ghost imaging via sparsity constraints.

A spatial multiplexing reconstruction method has been proposed to improve the sampling efficiency and image quality of Fourier-transform ghost imaging. In this method, the sensing equation of Fourier-transform ghost imaging is established based on recombination and reutilization of the correlated intensity distributions of light fields. It is theoretically proved that the scale of the sensing matrix in the sensing equation can be greatly reduced, and spatial multiplexing combined with this matrix reduction provides the feasibility of ghost imaging with just a few measurements.