Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers

Li, Yuhang; Luo, Yi; Bai, Bijie; Ozcan, Aydogan

doi:10.1109/jstqe.2022.3194574

Cited by 10 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In another example, 2 NNs were designed to enable imaging through scattering media, allowing all-optical reconstruction of unknown objects behind a random diffuser never seen during the training, as shown in Fig. 8o [205][206][207] . This demonstrates the generalization capability of this diffractive computational framework, revealing its robustness to unpredicted perturbations of the wavefront.…”

Section: Computational Terahertz Imaging Via Diffractive Processingmentioning

confidence: 99%

High-throughput terahertz imaging: progress and challenges

Li,

et al. 2023

Light Sci Appl

Self Cite

View full text Add to dashboard Cite

Many exciting terahertz imaging applications, such as non-destructive evaluation, biomedical diagnosis, and security screening, have been historically limited in practical usage due to the raster-scanning requirement of imaging systems, which impose very low imaging speeds. However, recent advancements in terahertz imaging systems have greatly increased the imaging throughput and brought the promising potential of terahertz radiation from research laboratories closer to real-world applications. Here, we review the development of terahertz imaging technologies from both hardware and computational imaging perspectives. We introduce and compare different types of hardware enabling frequency-domain and time-domain imaging using various thermal, photon, and field image sensor arrays. We discuss how different imaging hardware and computational imaging algorithms provide opportunities for capturing time-of-flight, spectroscopic, phase, and intensity image data at high throughputs. Furthermore, the new prospects and challenges for the development of future high-throughput terahertz imaging systems are briefly introduced.

show abstract

Section: Computational Terahertz Imaging Via Diffractive Processingmentioning

confidence: 99%

High-throughput terahertz imaging: progress and challenges

Li,

et al. 2023

Light Sci Appl

Self Cite

View full text Add to dashboard Cite

show abstract

“…The depth advantages that deeper diffractive architectures possess include better generalization capacity for all-optical inference tasks, which has been supported in the literature by both theoretical and empirical evidence. 29,31,[33][34][35][36][37] To quantitatively evaluate the impact of the number (K) of diffractive layers on the accuracy of optical information transfer through unknown random diffusers, we trained three hybrid models, where the architectures of the electronic encoder were kept identical, but the diffractive optical decoders had different numbers of trainable diffractive layers in each model. Figure 5 reports the output results of three exemplary handwritten digits and a test grating object information transferred through a new unknown random diffuser using these three hybrid models with K ¼ 2, 4, and 6.…”

Section: Impact Of the Number Of Diffractive Layers On The Optical In...mentioning

confidence: 99%

“…Encoding for Optical Information Transfer through Unknown Random Diffusers First, we analyze the impact of the encoder CNN on the optical information transfer through unknown random diffusers present in the optical path, and quantitatively explore its necessity, as opposed to a diffractive decoder that is trained alone. In this analysis, we compared it against the architecture of our previous work, 29,30 which was used to see amplitude objects through random diffusers using a diffractive neural network, as shown in Fig. 2 of random diffusers, successfully generalizing to see through new random diffusers never seen before.…”

Section: Design Of a Diffractive Decoder With Electronicmentioning

confidence: 99%

Optical information transfer through random unknown diffusers using electronic encoding and diffractive decoding

Li,

Gan,

Bai

et al. 2023

Adv. Photon.

Self Cite

View full text Add to dashboard Cite

Free-space optical information transfer through diffusive media is critical in many applications, such as biomedical devices and optical communication, but remains challenging due to random, unknown perturbations in the optical path. We demonstrate an optical diffractive decoder with electronic encoding to accurately transfer the optical information of interest, corresponding to, e.g., any arbitrary input object or message, through unknown random phase diffusers along the optical path. This hybrid electronic-optical model, trained using supervised learning, comprises a convolutional neural network-based electronic encoder and successive passive diffractive layers that are jointly optimized. After their joint training using deep learning, our hybrid model can transfer optical information through unknown phase diffusers, demonstrating generalization to new random diffusers never seen before. The resulting electronic-encoder and optical-decoder model was experimentally validated using a 3D-printed diffractive network that axially spans <70λ, where λ ¼ 0.75 mm is the illumination wavelength in the terahertz spectrum, carrying the desired optical information through random unknown diffusers. The presented framework can be physically scaled to operate at different parts of the electromagnetic spectrum, without retraining its components, and would offer low-power and compact solutions for optical information transfer in free space through unknown random diffusive media.

show abstract

“…These advantages make optical neural networks an attractive solution for applications that require fast and efficient information processing, such as real-time image and video processing, autonomous systems, and communication networks. [8][9][10][11][12][13][14][15] Optical neural networks were first reported in the 1980s but have gained popularity in recent years due to advancements in technology. Optical neural networks can be implemented as either free space [45][46][47][48][49][50][51][52][53][54][55] or integrated [56][57][58][59][60][61][62][63][64][65][66][67][68][69][70][71][72][73][74][75] versions, each with their own advantages and disadvantages.…”

Section: Introductionmentioning

confidence: 99%

Black-box simulation method: train the optical model from output

Hu¹,

Nouri²,

Dalir³

et al. 2023

Physics and Simulation of Optoelectronic Devices XXXI

View full text Add to dashboard Cite

Accurate simulation is a critical requirement for modern optical systems, but precise theoretical modeling can be challenging due to various factors such as misalignment, theoretical approximations, and instrument errors. This paper presents the black-box simulation method, which addresses these limitations by training the optical system model using the optical field outputs. This approach leads to more accurate simulations, making it possible to effectively train optical Neural Network systems for improved performance.

show abstract

Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers

Cited by 10 publications

References 32 publications

High-throughput terahertz imaging: progress and challenges

High-throughput terahertz imaging: progress and challenges

Optical information transfer through random unknown diffusers using electronic encoding and diffractive decoding

Black-box simulation method: train the optical model from output

Contact Info

Product

Resources

About