Wen-Kai Yu

Dong-Yin Wang, Shu-Hang Bie, Xi-Hao Chen et al.

A physics-driven generative adversarial network (GAN) was established here for single-pixel hyperspectral imaging (HSI) in the infrared spectrum, to eliminate the extensive data training work required by traditional data-driven model. Within the GAN framework, the physical process of single-pixel imaging (SPI) was integrated into the generator, and the actual and estimated one-dimensional (1D) bucket signals were employed as constraints in the objective function to update the network's parameters and optimize the generator with the assistance of the discriminator. In comparison to single-pixel infrared HSI methods based on compressed sensing and physics-driven convolution neural networks, our physics-driven GAN-based single-pixel infrared HSI can achieve higher imaging performance but with fewer measurements. We believe that this physics-driven GAN will promote practical applications of computational imaging, especially various SPI-based techniques.

Wen-Kai Yu, Ya-Xin Li, Jian Leng et al.

A secure optical communication requires both high transmission efficiency and high authentication performance, while existing cryptographic key distribution protocols based on ghost imaging have many shortcomings. Here, based on computational ghost imaging, we propose an interactive protocol that enables multi-party cryptographic key distribution over a public network and self-authentication by setting an intermediary that shares partial roles of the server. This fragment-synthesis-based authentication method may facilitate the remote distribution of cryptographic keys.

Shuo-Fei Wang, Wen-Kai Yu, Ya-Xin Li

Networks with large receptive field (RF) have shown advanced fitting ability in recent years. In this work, we utilize the short-term residual learning method to improve the performance and robustness of networks for image denoising tasks. Here, we choose a multi-wavelet convolutional neural network (MWCNN), one of the state-of-art networks with large RF, as the backbone, and insert residual dense blocks (RDBs) in its each layer. We call this scheme multi-wavelet residual dense convolutional neural network (MWRDCNN). Compared with other RDB-based networks, it can extract more features of the object from adjacent layers, preserve the large RF, and boost the computing efficiency. Meanwhile, this approach also provides a possibility of absorbing advantages of multiple architectures in a single network without conflicts. The performance of the proposed method has been demonstrated in extensive experiments with a comparison with existing techniques.

Wen-Kai Yu, An-Dong Xiong, Xu-Ri Yao et al.

This paper discusses the noisy phase retrieval problem: recovering a complex image signal with independent noise from quadratic measurements. Inspired by the dark fringes shown in the measured images of the array detector, a novel phase retrieval approach is proposed and demonstrated both theoretically and experimentally to recognize the dark fringes and bypass the invalid fringes. A more accurate relative phase ratio between arbitrary two pixels is achieved by calculating the multiplicative ratios (or the sum of phase difference) on the path between them. Then the object phase image can be reconstructed precisely. Our approach is a good choice for retrieving high-quality phase images from noisy signals and has many potential applications in the fields such as X-ray crystallography, diffractive imaging, and so on.