[HTML][HTML] Ultra-thin 3D lensless fiber endoscopy using diffractive optical elements and deep neural networks

R Kuschmierz, E Scharf… - Light: Advanced …, 2021 - light-am.com
Minimally invasive endoscopes are indispensable in biomedicine. Coherent fiber bundles
(CFBs) enable ultrathin lensless endoscopes. However, the propagation of light through a …

Harnessing disorder for photonic device applications

H Cao, Y Eliezer - Applied Physics Reviews, 2022 - pubs.aip.org
For photonic devices, structural disorder and light scattering have long been considered
annoying and detrimental features that were best avoided or minimized. This review shows …

Image transmission through a dynamically perturbed multimode fiber by deep learning

S Resisi, SM Popoff, Y Bromberg - Laser & Photonics Reviews, 2021 - Wiley Online Library
When multimode optical fibers are perturbed, the data that is transmitted through them is
scrambled. This presents a major difficulty for many possible applications, such as …

Seeing through multimode fibers with physics-assisted deep learning

H Gao, H Hu, Y Zhang, W Zhang, T Yan - Optics & Laser Technology, 2023 - Elsevier
High-fidelity image transmission through multimode fiber is critical for the biomedical
imaging and telecommunications industries. However, mode coupling and modal dispersion …

Deep learning image transmission through a multimode fiber based on a small training dataset

B Song, C Jin, J Wu, W Lin, B Liu, W Huang, S Chen - Optics express, 2022 - opg.optica.org
An improved deep neural network incorporating attention mechanism and DSSIM loss
function (AM_U_Net) is used to recover input images with speckles transmitted through a …

Super-resolution multimode fiber imaging with an untrained neural network

W Li, K Abrashitova, LV Amitonova - Optics Letters, 2023 - opg.optica.org
Multimode fiber endoscopes provide extreme miniaturization of imaging components for
minimally invasive deep tissue imaging. Typically, such fiber systems suffer from low spatial …

Generative adversarial network for superresolution imaging through a fiber

W Li, K Abrashitova, G Osnabrugge, LV Amitonova - Physical Review Applied, 2022 - APS
A multimode fiber represents the ultimate limit in miniaturization of imaging endoscopes.
However, such a miniaturization usually comes as a cost of a low spatial resolution and a …

Multiple side-coupled images recognition in plastic optical fibers based on deep learning

S Lu, C Wang, Z Tan - Optics Communications, 2023 - Elsevier
In recent years, the technology of multi-mode fiber (MMF) output speckle recognition has
been widely used in the fields of optical imaging, endoscope devices, and fiber optic sensor …

Single image detecting enhancement through scattering media based on transmission matrix with a deep learning network

W Zhang, S Zhou, X Sui, G Gu, Q Chen - Optics Communications, 2021 - Elsevier
Random scattering media that scatters incident light waves for optical diffraction-limit break
imaging has important application prospects and significance in biomedical imaging …

Benchmarking analysis of computer generated holograms for complex wavefront shaping using pixelated phase modulators

S Rothe, P Daferner, S Heide, D Krause… - Optics …, 2021 - opg.optica.org
Wavefront shaping with spatial light modulators (SLMs) enables aberration correction,
especially for light control through complex media, like biological tissues and multimode …