SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network

Karim, Nazmul; Rahnavard, Nazanin

doi:10.48550/arxiv.2107.01330

Cited by 6 publications

(7 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This physics-driven GAN-based image reconstruction method could be formulated as a min-max optimization problem (see Refs. [47,48]). min…”

Section: Image Reconstructionmentioning

confidence: 99%

Single-Pixel Infrared Hyperspectral Imaging via Physics-Guided Generative Adversarial Networks

Wang,

Bie,

Chen

et al. 2024

Photonics

View full text Add to dashboard Cite

A physics-driven generative adversarial network (GAN) was utilized to demonstrate a single-pixel hyperspectral imaging (HSI) experiment in the infrared spectrum, eliminating the need for extensive dataset training in most data-driven deep neural networks. Within the GAN framework, the physical process of single-pixel imaging (SPI) was integrated into the generator, and its estimated one-dimensional (1D) bucket signals and the actual 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 compressive sensing and physics-driven convolution neural networks, our physics-driven GAN-based single-pixel infrared HSI exhibits superior imaging performance. It requires fewer samples and achieves higher image quality. We believe that our physics-driven network will drive practical applications in computational imaging, including various SPI-based techniques.

show abstract

“…This physics-driven GAN-based image reconstruction method could be formulated as a min-max optimization problem (see Refs. [47,48]). min…”

Section: Image Reconstructionmentioning

confidence: 99%

Single-Pixel Infrared Hyperspectral Imaging via Physics-Guided Generative Adversarial Networks

Wang,

Bie,

Chen

et al. 2024

Photonics

View full text Add to dashboard Cite

show abstract

“…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

“…The progress of AI technology in recent years has been remarkable, and it has found applications in diverse areas, ranging from COVID-19 analysis [5,6] to finegrained image generation [7], and from non-uniform compressed sensing solutions [8] to SPI-GAN [9]. The widespread adoption of AI in various fields demonstrates its capability to address problems of varying complexity effectively.…”

Section: Introductionmentioning

confidence: 99%

NeuroMorphNet: A Multiscale Convolutional Neural Network for High-Precision Brain Tumor Segmentation in 3D Medical Images

Guennich,

Othmani,

Ltifi

2023

Preprint

View full text Add to dashboard Cite

The use of high-precision automatic algorithms to segment brain tumors offers the potential for improved disease diagnosis, treatment monitoring, as well as the possibility of large-scale pathological studies. In this study, we present a new 9-layer multiscale architecture dedicated to the semantic segmentation of 3D medical images, with a particular focus on brain tumor images, using convolutional neural networks. Our innovative solution draws inspiration from the Deepmedic architecture while incorporating significant enhancements. The use of variable-sized filters between layers and the early incorporation of residual connections from the very first layer greatly enhance the accuracy of 3D medical image segmentation. Additionally, the reduction in the number of layers in our dual-pathway network optimizes efficiency while maintaining exceptional performance. This combination of innovations, with Deepmedic as a starting point, positions our solution as a major advancement in the field of 3D medical image segmentation, offering an optimal balance between accuracy and efficiency for clinical applications.

show abstract

SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network

Cited by 6 publications

References 71 publications

Single-Pixel Infrared Hyperspectral Imaging via Physics-Guided Generative Adversarial Networks

Single-Pixel Infrared Hyperspectral Imaging via Physics-Guided Generative Adversarial Networks

VGenNet: Variable Generative Prior Enhanced Single Pixel Imaging

NeuroMorphNet: A Multiscale Convolutional Neural Network for High-Precision Brain Tumor Segmentation in 3D Medical Images

Contact Info

Product

Resources

About