Diffractive Deep Neural Networks at Visible Wavelengths

Chen, Hang; Feng, Jianan; Jiang, Minwei; Wang, Yudong; Lin, Jie; Tan, Jiubin; Jin, Peng

doi:10.1016/j.eng.2020.07.032

Cited by 104 publications

(52 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[55,56] Fabrication and assembly of such diffractive QPI systems operating in the visible and near IR wavelengths can be achieved using two-photon polymerization-based 3D printing methods as well as optical lithography tools. [69][70][71]…”

Section: Discussionmentioning

confidence: 99%

All‐Optical Phase Recovery: Diffractive Computing for Quantitative Phase Imaging

Mengü

Ozcan

2022

Advanced Optical Materials

View full text Add to dashboard Cite

Quantitative phase imaging (QPI) is a label‐free computational imaging technique that provides optical path length information of specimens. In modern implementations, the quantitative phase image of an object is reconstructed digitally through numerical methods running in a computer, often using iterative algorithms. Here, a diffractive QPI network that can perform all‐optical phase recovery is demonstrated, and the quantitative phase image of an object is synthesized by converting the input phase information of a scene into intensity variations at the output plane. A diffractive QPI network is a specialized all‐optical processor designed to perform a quantitative phase‐to‐intensity transformation through passive diffractive surfaces that are spatially engineered using deep learning and image data. Forming a compact, all‐optical network that axially extends only ≈200–300λ, where λ is the illumination wavelength, this framework can replace traditional QPI systems and related digital computational burden with a set of passive transmissive layers. All‐optical diffractive QPI networks can potentially enable power‐efficient, high frame‐rate, and compact phase imaging systems that might be useful for various applications, including, e.g., microscopy and sensing.

show abstract

Section: Discussionmentioning

confidence: 99%

All‐Optical Phase Recovery: Diffractive Computing for Quantitative Phase Imaging

Mengü

Ozcan

2022

Advanced Optical Materials

View full text Add to dashboard Cite

show abstract

“…In addition, the mr -MDA, employing the proposed training strategy, is insensitive to the spatial information of targets, which is a key feature when utilizing an arrayed photonic integrated device to recognize complex 3D objects in a dynamic and rapid manner with low-energy consumption. Although it is currently difficult to perfectly align more diffractive layers, related work has been published that analyzes the errors in model placement [ 40 ]. In addition, the model used in this article provides a way in which to avoid excessively deep network layers.…”

Section: Discussionmentioning

confidence: 99%

The mr-MDA: An Invariant to Shifting, Scaling, and Rotating Variance for 3D Object Recognition Using Diffractive Deep Neural Network

Zhou

Zhang

2022

Sensors

View full text Add to dashboard Cite

The diffractive deep neural network (D2NN) can efficiently accomplish 2D object recognition based on rapid optical manipulation. Moreover, the multiple-view D2NN array (MDA) possesses the obvious advantage of being able to effectively achieve 3D object classification. At present, 3D target recognition should be performed in a high-speed and dynamic way. It should be invariant to the typical shifting, scaling, and rotating variance of targets in relatively complicated circumstances, which remains a shortcoming of optical neural network architectures. In order to efficiently recognize 3D targets based on the developed D2NN, a more robust MDA (mr-MDA) is proposed in this paper. Through utilizing a new training strategy to tackle several random disturbances introduced into the optical neural network system, a trained mr-MDA model constructed by us was numerically verified, demonstrating that the training strategy is able to dynamically recognize 3D objects in a relatively stable way.

show abstract

“…Computing using diffractive networks possesses the benefits of high speed, parallelism and low power consumption: the computational task of interest is completed while the incident light passes through passive thin diffractive layers at the speed of light, requiring no energy other than the illumination. This framework's success and capabilities were demonstrated numerically and experimentally by achieving various computational tasks, including object classification [24][25][26][27] , hologram reconstruction 28 , quantitative phase imaging 29 , privacy-preserving class-specific imaging 30 , logic operations 31,32 , universal linear transformations 33 , polarization processing 34 among others [35][36][37][38][39][40][41][42][43][44] . Diffractive networks can also process and shape the phase and amplitude of broadband input spectra to perform various tasks such as pulse shaping 45 , wavelength-division multiplexing 46 and single-pixel image classification 47 .…”

Section: Introductionmentioning

confidence: 99%

Seeing through unknown, random diffusers using all-optical diffractive networks

Luo

Zhao

et al. 2022

AI and Optical Data Sciences III

View full text Add to dashboard Cite

Classification of an object behind a random and unknown scattering medium sets a challenging task for computational imaging and machine vision fields. Recent deep learning-based approaches demonstrated the classification of objects using diffuser-distorted patterns collected by an image sensor. These methods demand relatively large-scale computing using deep neural networks running on digital computers. Here, we present an all-optical processor to directly classify unknown objects through unknown, random phase diffusers using broadband illumination detected with a single pixel. A set of transmissive diffractive layers, optimized using deep learning, forms a physical network that all-optically maps the spatial information of an input object behind a random diffuser into the power spectrum of the output light detected through a single pixel at the output plane of the diffractive network. We numerically demonstrated the accuracy of this framework using broadband radiation to classify unknown handwritten digits through random new diffusers, never used during the training phase, and achieved a blind testing accuracy of 88.53%. This single-pixel all-optical object classification system through random diffusers is based on passive diffractive layers that process broadband input light and can operate at any part of the electromagnetic spectrum by simply scaling the diffractive features proportional to the wavelength range of interest. These results have various potential applications in, e.g., biomedical imaging, security, robotics, and autonomous driving.

show abstract

Diffractive Deep Neural Networks at Visible Wavelengths

Cited by 104 publications

References 36 publications

All‐Optical Phase Recovery: Diffractive Computing for Quantitative Phase Imaging

All‐Optical Phase Recovery: Diffractive Computing for Quantitative Phase Imaging

The mr-MDA: An Invariant to Shifting, Scaling, and Rotating Variance for 3D Object Recognition Using Diffractive Deep Neural Network

Seeing through unknown, random diffusers using all-optical diffractive networks

Contact Info

Product

Resources

About