Showing papers by "Guohai Situ published in 2023"

Lensless complex amplitude demodulation based on deep learning in holographic data storage

Abstract: To increase the storage capacity in holographic data storage (HDS), the information to be stored is encoded into a complex amplitude. Fast and accurate retrieval of amplitude and phase from the reconstructed beam is necessary during data readout in HDS. In this study, we proposed a complex amplitude demodulation method based on deep learning from a single-shot diffraction intensity image and verified it by a non-interferometric lensless experiment demodulating four-level amplitude and four-level phase. By analyzing the correlation between the diffraction intensity features and the amplitude and phase encoding data pages, the inverse problem was decomposed into two backward operators denoted by two convolutional neural networks (CNNs) to demodulate amplitude and phase respectively. The experimental system is simple, stable, and robust, and it only needs a single diffraction image to realize the direct demodulation of both amplitude and phase. To our investigation, this is the first time in HDS that multilevel complex amplitude demodulation is achieved experimentally from one diffraction intensity image without iterations.

VGenNet: Variable Generative Prior Enhanced Single Pixel Imaging

Abstract: 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 detection problem. Thus, it is crucially important to develop efficient SPI techniques for image reconstruction from the 1D measurements, in particular, an undersampled one. Recently, various studies have demonstrated the superiority of deep learning for SPI. However, due to the generalization issue, conventional data-driven deep learning is a task-specific approach. One needs to retrain the neural network for different SPI imaging problems and different types of objects. Here, we propose a variable generative network enhanced SPI algorithm (VGenNet) by incorporating a model-driven fine-tuning process into a generative model that may have been trained for other tasks. VGenNet simultaneously updates the input vector and the weights in a generator to generate feasible solutions that reproduce the raw measurements. We demonstrate the proposed technique with indoor SPI and outdoor 3D single-pixel LiDAR experiments. Our results show that high-quality images can be reconstructed at low sampling ratios under different system configurations, demonstrating the good performance and flexibility of VGenNet. Overall, the proposed VGenNet is a general framework to take advantage of both the data and physics priors, allowing the direct use of a pretrained generative model to solve various inverse imaging problems.

DeepSCI: scalable speckle correlation imaging using physics-enhanced deep learning.

Abstract: In this Letter we present a physics-enhanced deep learning approach for speckle correlation imaging (SCI), i.e., DeepSCI. DeepSCI incorporates the theoretical model of SCI into both the training and test stages of a neural network to achieve interpretable data preprocessing and model-driven fine-tuning, allowing the full use of data and physics priors. It can accurately reconstruct the image from the speckle pattern and is highly scalable to both medium perturbations and domain shifts. Our experimental results demonstrate the suitability and effectiveness of DeepSCI for solving the problem of limited generalization generally encountered in data-driven approaches.

Learning-based adaptive under-sampling for Fourier single-pixel imaging.

Abstract: In this Letter, we present a learning-based method for efficient Fourier single-pixel imaging (FSI). Based on the auto-encoder, the proposed adaptive under-sampling technique (AuSamNet) manages to optimize a sampling mask and a deep neural network at the same time to achieve both under-sampling of the object image's Fourier spectrum and high-quality reconstruction from the under-sampled measurements. It is thus helpful in determining the best encoding and decoding scheme for FSI. Simulation and experiments demonstrate that AuSamNet can reconstruct high-quality natural color images even when the sampling ratio is as low as 7.5%. The proposed adaptive under-sampling strategy can be used for other computational imaging modalities, such as tomography and ptychography. We have released our source code.

Dammann gratings-based truly parallel optical matrix multiplication accelerator.

Abstract: Matrix multiplication (MM) is a fundamental operation in various scientific and engineering computations, as well as in artificial intelligence algorithms. Efficient implementation of MM is crucial for speeding up numerous applications. Photonics presents an opportunity for efficient acceleration of dense matrix computation, owing to its intrinsic advantages, such as huge parallelism, low latency, and low power consumption. However, most optical matrix computing architectures have been limited to realizing single-channel vector-matrix multiplication or using complex configurations to expand the number of channels, which does not fully exploit the parallelism of optics. In this study, we propose a novel, to the best of our knowledge, scheme for the implementation of large-scale two-dimensional optical MM with truly massive parallelism based on a specially designed Dammann grating. We demonstrate a sequence of MMs of 50 pairs of randomly generated 4 × 8 and 8 × 4 matrices in our proof-of-principle experiment. The results indicate that the mean relative error is approximately 0.048, thereby demonstrating optical robustness and high accuracy.

Defogging lens design for infrared laser active imaging by orbital angular momentum meta-surface

Abstract: Imaging in scattering media has been a big problem, as the ballistic light carrying object information is swamped by background noise, thus degrading the imaging quality. In addressing this issue, active illumination imaging technology has various advantages over passive imaging since it can introduce several controllable parameters, such as polarization, coded aperture, and so on. Here, we actively introduce orbital angular momentum into the scattering imaging, which can effectively enhance the mid/high frequency components of the object. Then, it is fused with the low-quality image obtained by traditional imaging, which can effectively enhance the visualization. Compared with the results of direct imaging, the signal-to-noise ratio is improved by up to 250%–300%, and the image contrast is improved by up to 300%–400%. This method may find applications in foggy environments for autonomous driving, lidar, and machine vision.

Multifunctional Metasurfaces Enabled by Multifold Geometric Phase Interference.

Abstract: Geometric phase is frequently used in artificially designed metasurfaces; it is typically used only once in reported works, leading to conjugate responses of two spins. Supercells containing multiple nanoantennas can break this limitation by introducing more degrees of freedom to generate new modulation capabilities. Here, we provide a method for constructing supercells for geometric phases using triple rotations, each of which achieves a specific modulation function. The physical meaning of each rotation is revealed by stepwise superposition. Based on this idea, spin-selective holography, nanoprinting, and their hybrid displays are demonstrated. As a typical application, we have designed a metalens that enables spin-selective transmission, allowing for high-quality imaging with only one spin state, which can serve as a plug-and-play chiral detection device. Finally, we analyzed how the size of supercells and the phase distribution inside it can affect the higher order diffraction, which may help in designing supercells for different scenarios.