Single-arm ghost imaging via conditional generative adversarial network

Zhao, Ming; Zhang, Xuedian; Zhang, Rongfu

doi:10.1088/1612-202x/ac0153

Cited by 4 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The generative adversarial network (GAN) has also been used for SPI, in which the discriminator introduces adversarial error into the loss function. The GAN-based method is able to achieve better results due to the advanced adversarial training strategy. − Other studies are mainly carried out from the aspects of learning method, , network structure, , and the combination with specific applications. − …”

Section: Introductionmentioning

confidence: 99%

VGenNet: Variable Generative Prior Enhanced Single Pixel Imaging

et al. 2023

View full text Add to dashboard Cite

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 datadriven 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.

show abstract

Section: Introductionmentioning

confidence: 99%

VGenNet: Variable Generative Prior Enhanced Single Pixel Imaging

et al. 2023

View full text Add to dashboard Cite

show abstract

“…During the last few years, artificial neural networks have grown rapidly and there are many famous kinds of models, such as BP neural network (BPNN) [11,12], hopfield NN [13,14] and many others [15][16][17][18][19]. In practical application, BPNN is the most widely used in various fields.…”

Section: Introductionmentioning

confidence: 99%

Forward kinematics of body posture perception using an improved BP neural network based on a quantum genetic algorithm

Chen¹,

Zhang²,

Liu³

et al. 2022

Laser Phys. Lett.

View full text Add to dashboard Cite

Forward kinematics analysis of body posture perception is the basis for studying other performance of 6-degree of freedom parallel robot. Because forward kinematics involves many sets of nonlinear equations, it is usually difficult to solve. In this paper, an improved BP neural network (BPNN) based on a quantum genetic algorithm (GA) is designed to solve the forward kinematics problem. Additionally, we use the characteristics of easy calculation of inverse kinematics to generate a dataset for training and testing. Finally, through a large number of experiments, we show that the improved strategy of BPNN by quantum GA is effective, and the accuracy of the model we designed is high enough to solve the forward kinematics of body posture perception.

show abstract

Sampling Rate Setting in Convolutional Neural Network Ghost Imaging

Yang

Feng

2023

J Russ Laser Res

View full text Add to dashboard Cite

Single-arm ghost imaging via conditional generative adversarial network

Cited by 4 publications

References 37 publications

VGenNet: Variable Generative Prior Enhanced Single Pixel Imaging

VGenNet: Variable Generative Prior Enhanced Single Pixel Imaging

Forward kinematics of body posture perception using an improved BP neural network based on a quantum genetic algorithm

Sampling Rate Setting in Convolutional Neural Network Ghost Imaging

Contact Info

Product

Resources

About