Deep Learning Imaging through Fully-Flexible Glass-Air Disordered Fiber

Zhao, Jian; Sun, Yangyang; Zhu, Zheyuan; Antonio-López, Jose Enrique; Correa, Rodrigo Amezcua; Pang, Shuo; Schülzgen, Axel

doi:10.1021/acsphotonics.8b00832

Cited by 37 publications

(29 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, Karbasi, et al reported the first observation of TAL in disordered optical fibers [13][14][15]. The disordered optical fibers have since been used for high-quality image transport [22][23][24][25][26], beam multiplexing [27], wave-front shaping and sharp focusing [28][29][30], nonlocal nonlinearity [31,32], single-photon data packing [33], optical diagnostics [34], and random lasers [35,36].…”

Section: Introductionmentioning

confidence: 99%

Group velocity distribution and short-pulse dispersion in a disordered transverse Anderson localization optical waveguide

Mafi

2019

Optical Fiber Technology

View full text Add to dashboard Cite

We investigate the group velocity distribution of waveguide modes in the presence of disorder. The results are based on extensive numerical simulations of disordered optical waveguides using statistical methods. We observe that the narrowest distribution of group velocities is obtained in the presence of a small amount of disorder; therefore, the modal dispersion of an optical pulse is minimized when there is only a slight disorder in the waveguide. The absence of disorder or the presence of a large amount of disorder can result in a large modal dispersion due to the broadening of the distribution of the group velocities. We devise a metric that can be applied to the mode group index probability-density-function and predict the optimal level of disorder that results in the lowest amount of modal dispersion for short pulse propagation. Our results are important for studying the propagation of optical pulses in the linear regime, e.g., for optical communications; and the nonlinear regime for high-power short-pulse propagation. arXiv:1909.05928v2 [physics.optics]

show abstract

Section: Introductionmentioning

confidence: 99%

Group velocity distribution and short-pulse dispersion in a disordered transverse Anderson localization optical waveguide

Mafi

2019

Optical Fiber Technology

View full text Add to dashboard Cite

show abstract

“…The fast inference and the ability of learning a versatile mapping from measurement to signal contribute to the wide adoption of neural networks in recent years [16]- [20]. Most of these approaches use a neural network with parameters θ to approximate the inverse mapping A inv (g) based on a series of observations {f i }.…”

Section: Introductionmentioning

confidence: 99%

Signal Retrieval With Measurement System Knowledge Using Variational Generative Model

et al. 2020

Self Cite

View full text Add to dashboard Cite

Signal retrieval from a series of indirect measurements is a common task in many imaging, metrology, and characterization platforms in science and engineering. Because most of the indirect measurement processes are well-described by physical models, signal retrieval can be solved with an iterative optimization that enforces measurement consistency and prior knowledge on the signal. These iterative algorithms are time-consuming and only accommodate a linear measurement process and convex signal constraints. Recently, neural networks have been widely adopted to supersede iterative methods by directly approximating the inverse mapping of the measurement process. However, such vanilla network with a deterministic multi-layer structure is unable to distinguish signal ambiguities in ill-posed measurement systems, and the retrieved signals often lack consistency with the measurement. In this work, we incorporate the known measurement process into a customized variational generative model to capture the distribution of all possible signals given a measurement, which can be either a linear or nonlinear process. Our signal retrieval framework resolves the ambiguity in the measurement process, and retrieves high-fidelity signals that satisfy the physical model in a variety of nonlinear, ill-posed systems, such as image retrieval from Fresnel hologram and ultrafast pulse retrieval. INDEX TERMS Variational generative model, computational imaging, neural networks, inverse problem.

show abstract

“…In addition, deep learning has been used in optical communications [58,59], and more specifically, for real-time fibre mode demodulation [60], end-to-end fibre communications [61], and improvement in fibre transmission [62]. Imaging has also been demonstrated using microstructured fibre [63] and multimode fibre array [64] with deep learning.…”

Section: Introductionmentioning

confidence: 99%

Fibre-optic based particle sensing via deep learning

et al. 2019

View full text Add to dashboard Cite

We demonstrate the capability for the identification of single particles, via a neural network, directly from the backscattered light collected by a 30-core optical fibre, when particles are illuminated using a single mode fibre-coupled laser light source. The neural network was shown to be able to determine the specific species of pollen with ∼97% accuracy, along with the distance between the end of the 30core sensing fibre and the particles, with an associated error of±6 μm. The ability to be able to classify particles directly from backscattered light using an optical fibre has potential in environments in which transmission imaging is neither possible nor suitable, such as sensing over opaque media, in the deep sea or outer space.

show abstract

Deep Learning Imaging through Fully-Flexible Glass-Air Disordered Fiber

Cited by 37 publications

References 31 publications

Group velocity distribution and short-pulse dispersion in a disordered transverse Anderson localization optical waveguide

Group velocity distribution and short-pulse dispersion in a disordered transverse Anderson localization optical waveguide

Signal Retrieval With Measurement System Knowledge Using Variational Generative Model

Fibre-optic based particle sensing via deep learning

Contact Info

Product

Resources

About