Integration of Programmable Diffraction with Digital Neural Networks
Not on the map. Why?
Abstract (arXiv)
Optical imaging and sensing systems based on diffractive elements have seen massive advances over the last several decades. Earlier generations of diffractive optical processors were, in general, designed to deliver information to an independent system that was separately optimized, primarily driven by human vision or perception. With the recent advances in deep learning and digital neural networks, there have been efforts to establish diffractive processors that are jointly optimized with digital neural networks serving as their back-end. These jointly optimized hybrid (optical+digital) processors establish a new "diffractive language" between input electromagnetic waves that carry analog information and neural networks that process the digitized information at the back-end, providing the best of both worlds. Such hybrid designs can process spatially and temporally coherent, partially coherent, or incoherent input waves, providing universal coverage for any spatially varying set of point spread functions that can be optimized for a given task, executed in collaboration with digital neural networks. In this article, we highlight the utility of this exciting collaboration between engineered and programmed diffraction and digital neural networks for a diverse range of applications. We survey some of the major innovations enabled by the push-pull relationship between analog wave processing and digital neural networks, also covering the significant benefits that could be reaped through the synergy between these two complementary paradigms.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 58 of its 171 references that are in the map. First posted on arXiv 15 Jun 2024.
Builds on
58 of 171 references.
References · 58
- 2018All-Optical Machine Learning Using Diffractive Deep Neural Networkscited by 177
- 2018Universality of Deep Convolutional Neural Networkscited by 176
- 2023Art and the science of generative AI: A deeper divecited by 95
- 2016Neuromorphic Silicon Photonic Networkscited by 68
- 2020Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unitcited by 65
- 2020Deep neural networks for the evaluation and design of photonic devicescited by 50
- 2018Training of photonic neural networks through in situ backpropagationcited by 45
- 2019Nonlinear Approximation and (Deep) ReLU Networkscited by 45
- 2022Deep Learning-enabled Virtual Histological Staining of Biological Samplescited by 42
- 2020Single-shot Hyperspectral-Depth Imaging with Learned Diffractive Opticscited by 39
- 2020Misalignment Resilient Diffractive Optical Networkscited by 33
- 2018Analysis of Diffractive Optical Neural Networks and Their Integration with Electronic Neural Networkscited by 30
38 more
- 2018A Generative Model for Inverse Design of Metamaterialscited by 27
- 2019Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networkscited by 27
- 2021All-Optical Synthesis of an Arbitrary Linear Transformation Using Diffractive Surfacescited by 24
- 2019Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learningcited by 22
- 2019Digital Electronics and Analog Photonics for Convolutional Neural Networks (DEAP-CNNs)cited by 22
- 2022Diffractive all-optical computing for quantitative phase imagingcited by 22
- 2022To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objectscited by 21
- 2016DeepBinaryMask: Learning a Binary Mask for Video Compressive Sensingcited by 20
- 2021Computational Imaging Without a Computer: Seeing Through Random Diffusers at the Speed of Lightcited by 19
- 2018Physics-based Learned Design: Optimized Coded-Illumination for Quantitative Phase Imagingcited by 18
- 2019Data-Driven Design for Fourier Ptychographic Microscopycited by 18
- 2023Universal Linear Intensity Transformations Using Spatially-Incoherent Diffractive Processorscited by 17
- 2019Designing nanophotonic structures using conditional-deep convolutional generative adversarial networkscited by 16
- 2022Snapshot Multispectral Imaging Using a Diffractive Optical Networkcited by 16
- 2022Data class-specific all-optical transformations and encryptioncited by 16
- 2018Freeform Diffractive Metagrating Design Based on Generative Adversarial Networkscited by 13
- 2022Meta-optic Accelerators for Object Classifierscited by 13
- 2022Super-resolution image display using diffractive decoderscited by 13
- 2022Unidirectional Imaging using Deep Learning-Designed Materialscited by 13
- 2021Computer-free, all-optical reconstruction of holograms using diffractive networkscited by 12
- 2023Multispectral Quantitative Phase Imaging Using a Diffractive Optical Networkcited by 10
- 2018Illumination Pattern Design with Deep Learning for Single-Shot Fourier Ptychographic Microscopycited by 9
- 2020Deep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Aperturescited by 9
- 2020High-throughput molecular imaging via deep learning enabled Raman spectroscopycited by 9
- 2022Massively Parallel Universal Linear Transformations using a Wavelength-Multiplexed Diffractive Optical Networkcited by 9
- 2023Universal Polarization Transformations: Spatial programming of polarization scattering matrices using a deep learning-designed diffractive polarization transformercited by 8
- 2023Photonic Advantage of Optical Encoderscited by 8
- 2023All-Optical Phase Conjugation Using Diffractive Wavefront Processingcited by 8
- 2021Neural network-based image reconstruction in swept-source optical coherence tomography using undersampled spectral datacited by 6
- 2024Information hiding cameras: optical concealment of object information into ordinary imagescited by 6
- 2019Intelligent Metasurface Imager and Recognizercited by 5
- 2019Automated screening of sickle cells using a smartphone-based microscope and deep learningcited by 5
- 2023Learning Diffractive Optical Communication Around Arbitrary Opaque Occlusionscited by 5
- 2017Data Driven Coded Aperture Design for Depth Recoverycited by 4
- 2020Feature visualization of Raman spectrum analysis with deep convolutional neural networkcited by 4
- 2020MetaSensing: Intelligent Metasurface Assisted RF 3D Sensing by Deep Reinforcement Learningcited by 4
- 2022Analysis of Diffractive Neural Networks for Seeing Through Random Diffuserscited by 4
- 2022Time-lapse image classification using a diffractive neural networkcited by 4
50 most cited of 58 All 58 (JSON)
Built on by
Citing papers per year: 2024: 1.
1 paper.