Single-arm ghost imaging via conditional generative adversarial network

Abstract

In this study, we develop a single-arm ghost imaging (GI) framework based on a conditional generative adversarial network (cGAN) to improve the image quality and extend the application scenarios of GI. A set of one-dimensional (1D) bucket signals generated by a single-arm GI system and their corresponding ground-truth counterparts is employed to train the cGAN. This allows us to reconstruct a low-noise image from a new 1D bucket signal, while the sequence of random patterns is unnecessary. The results show that the proposed method significantly improves the image quality relative to the conventional GI methods.