摘要近年来, 深度学习技术的爆发式发展引领了机器学习的又一次浪潮. 深度神经网络具备抽象
特征的高效识别与提取能力, 强大的非线性拟合能力, 抗干扰鲁棒性及非凡的泛化能力 …

Since the advent of single-pixel imaging and machine learning, both fields have flourished,
but followed parallel tracks. Until recently, machine learning, especially deep learning, has …

Single-pixel imaging (SPI) is an emerging imaging methodology that converts a two-or even
three-dimensional image acquisition problem into a one-dimensional (1D) temporal-signal …

Here, we propose an encryption scheme by computational ghost imaging (CGI), and the
transmitting data have been hidden in the illumination patterns. The sender uses a set of key …

Deep learning has been broadly applied to imaging in scattering applications. A common
framework is to train a descattering network for image recovery by removing scattering …

Polarization computational ghost imaging (PCGI) often requires a large number of samples
to reconstruct the targets, which can be optimized by reducing sampling rates with the aids …

In this study, we proposed a self-supervised image-loop neural network (ILNet) with a part-
based model for single-pixel imaging (SPI). ILNet employs a part-based model that divides …

In this Letter, we propose a learning-based correction method to realize ghost imaging (GI)
through dynamic scattering media using deep neural networks with Gaussian constraints …

In this study, we proposed an underwater ghost imaging (GI) method based on a self-
supervised information extraction network (IEGI), which comprises two modules: speckle …

When the conventional optical coherence tomography (OCT) measures the transmittance
and the absorbance of the target in the scattering media, its image is affected by the …