0.8% Nyquist computational ghost imaging via non-experimental deep learning

We present a framework for computational ghost imaging based on deep learning and customized pink noise speckle patterns. The deep neural network in this work, which can learn the sensing model and enhance image reconstruction quality, is trained merely by simulation. The conventional computational ghost imaging results, deep learning-based ghost imaging results with white and pink noise are compared under multiple sampling ratios at different noise conditions. The experiments are done with digits, English letters, and Chinese characters. We show that the proposed scheme can provide high-quality images with a sampling ratio as low as 0.8% even when the object is outside the training dataset and robust to noisy environments. The method can be applied to a wide range of applications, including those requiring a low sampling ratio, fast reconstruction, or experiencing strong noise interference.