Maria Cywińska

YOSO: single-frame Gerchberg–Saxton phase retrieval with AI-based data augmentation for in-line holography

Julianna Winnik, Adam Walocha, Wojciech Ogonowski, Wiktor Forjasz et autres

Abstract We present YOSO (you only shot once), a single-frame phase retrieval framework for digital in-line holographic microscopy (DIHM) in which supervised deep learning is used to numerically generate an additional hologram corresponding to different defocus distance, creating a so-called multi-height dataset, …

pl, bg, es, de (code pays fourni par la source)

Computational adaptive optics for interferometric microscopy based on Bayesian inference

Emilia Wdowiak, Michał Józwik, Maria Cywińska

pl (code pays fourni par la source)

YOSO: single-frame Gerchberg-Saxton phase retrieval with AI-based data augmentation for in-line holography

Julianna Winnik, Adam Walocha, Wojciech Ogonowski, Wiktor Forjasz et autres

We present YOSO (You Only Shot Once), a single-frame phase retrieval framework for digital in-line holographic microscopy (DIHM) in which supervised deep learning is used to numerically generate an additional hologram corresponding to different defocus distance, creating a so-called multi-height dataset, which …

pl, es (code pays fourni par la source)

YOSO dataset: in-line holograms from experiments and simulation, and trained models for YOSO reconstruction

Julianna Winnik, Adam Walocha, Wojciech Ogonowski, Wiktor Forjasz et autres

This dataset contains in-line holograms: stinkbug.h – simulated in-line hologram of a phase sample given by a stinkbug.jpg distribution from matplotlib.image (z = 3.56 mm, Δ = 2.4 μm, λ = 0.561 μm) phase_test.h – hologram of a phase test target captured …

pl, es (code pays fourni par la source)

YOSO dataset: in-line holograms from experiments and simulation, and trained models for YOSO reconstruction

Julianna Winnik, Adam Walocha, Wojciech Ogonowski, Wiktor Forjasz et autres

This dataset contains in-line holograms: stinkbug.h – simulated in-line hologram of a phase sample given by a stinkbug.jpg distribution from matplotlib.image (z = 3.56 mm, Δ = 2.4 μm, λ = 0.561 μm) phase_test.h – hologram of a phase test target captured …

pl, es (code pays fourni par la source)

Single-interferogram wide-field Bayesian analysis for geometrical characterization of nanophotonic elements

Damian Suski, Maria Cywińska, Julianna Winnik, Michał Józwik et autres

Optimization-based algorithm for single-frame interferometric nanometrology of semiconductor structures

Damian Suski, Maria Cywińska, Julianna Winnik, Michał Józwik et autres

Operational limits of DeepQuadrature: AI-driven fringe analysis for optical and biological metrology

Wiktor Forjasz, Julianna Winnik, Wojciech Ogonowski, Michał Józwik et autres

Uncertainty‐Aware Bayesian Computational Imaging for Single‐Shot Widefield Interferometric Nanometrology

Damian Suski, Maria Cywińska, Julianna Winnik, Michał Józwik et autres

ABSTRACT Widefield interferometry offers non‐destructive, scalable nanometrology for semiconductor photonics, but prevailing pipelines require multi‐frame scanning (or phase‐shifting) and postprocessing of reconstructed noise‐limited phase, and do not provide single‐shot, geometry‐level uncertainties. We introduce an uncertainty‐aware Bayesian computational imaging framework that estimates semiconductor …

pl, no (code pays fourni par la source)

DeepBessel: deep learning-based full-field vibration profilometry using single-shot time-averaged interference microscopy

Maria Cywińska, Wiktor Forjasz, Emilia Wdowiak, Michal Jozwik et autres

Full-field vibration profilometry is essential for dynamic characterizing microelectromechanical systems (MEMS/MOEMS). Time-averaged interferometry (TAI) encodes spatial information about MEMS or MOEMS vibration amplitude in the interferogram's amplitude modulation using Bessel function (besselogram). Classical approaches for interferogram analysis are specialized for cosine function …

Single-shot Deep-learning-based Phase Imaging of Dense Biological Samples

Maria Cywińska, Wiktor Forjasz, Wojciech Ogonowski, Julianna Winnik et autres

DeepQuadrature enables adaptive single-shot phase demodulation for dense biological samples. Compared with the Hilbert Spiral Transform, it preserves fine structural detail under complex fringe geometry and suggests practical mitigation strategies for challenging local variations.

pl, no (code pays fourni par la source)

Attention-Enhanced DeepBessel Neural Network for Full-Field Vibration Profilometry

Wiktor Forjasz, Maria Cywińska, Julianna Winnik, Emilia Wdowiak et autres

This study introduces an attention-augmented extension of the DeepBessel convolutional neural network for reconstruction of vibration amplitude distributions from time-averaged interferograms, aiming to improve feature weighting, reduce Bessel-related artifacts, and enhance prediction accuracy.

pl (code pays fourni par la source)