Single photon counting compressive imaging using a generative model optimized via sampling and transfer learning.

Single photon counting compressive imaging, a combination of single-pixel-imaging and single-photon-counting technology, is provided with low cost and ultra-high sensitivity. However, it requires a long imaging time when applying traditional compressed sensing (CS) reconstruction algorithms. A deep-learning-based compressed reconstruction network refrains iterative computation while achieving efficient reconstruction. This paper proposes a compressed reconstruction network (OGTM) based on a generative model, adding sampling sub-network to achieve joint-optimization of sampling and generation for better reconstruction. To avoid the slow convergence caused by alternating training, initial weights of the sampling and generation sub-network are transferred from an autoencoder. The results indicate that the convergence speed and imaging quality are significantly improved. The OGTM validated on a single-photon compressive imaging system performs imaging experiments on specific and generalized targets. For specific targets, the results demonstrate that OGTM can quickly generate images from few measurements, and its reconstruction is better than the existing compressed sensing recovery algorithms, compensating defects of the generative models in compressed sensing.

Deep-learning-based single-photon-counting compressive imaging via jointly trained subpixel convolution sampling.

The combination of single-pixel-imaging and single-photon-counting technology can achieve ultrahigh-sensitivity photon-counting imaging. However, its applications in high-resolution and real-time scenarios are limited by the long sampling and reconstruction time. Deep-learning-based compressive sensing provides an effective solution due to its ability to achieve fast and high-quality reconstruction. This paper proposes a sampling and reconstruction integrated neural network for single-photon-counting compressive imaging. To effectively remove the blocking artefact, a subpixel convolutional layer is jointly trained with a deep reconstruction network to imitate compressed sampling. By modifying the forward and backward propagation of the network, the first layer is trained into a binary matrix, which can be applied to the imaging system. An improved deep-reconstruction network based on the traditional Inception network is proposed, and the experimental results show that its reconstruction quality is better than existing deep-learning-based compressive sensing reconstruction algorithms.

Self-assembly of tetrapod-shaped CdS nanostructures into 3D networks by a transverse growth process.

Spontaneous formation of 3D tetrapod-shaped CdS nanostructure networks has been achieved for the first time by vapor diffusion-deposition growth from CdS powders. The growth mechanism of the hexagonal and preferentially oriented CdS tetrapod-shaped nanostructures is a combination of the classic vapor-liquid-solid and vapor-solid processes, and the formation of a 3D network results from the spontaneous growths along the longitudinal and across the axial directions of the primarily formed CdS nanorods. Micro-photoluminescence measurements and near-field scanning optical microscopy investigations show that the synthesized CdS tetrapod networks have an excellent luminescence property and can be used as an optical waveguide cavities in which the guided light can be extremely confined.