Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Noise2Ghost: self-supervised deep convolutional reconstruction for ghost imaging.

Mathieu Manni, Dmitry Karpov, Kees Joost Batenburg

|July 2, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Deconvolution

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

Electron Microscope Tomography and Single-particle Reconstruction

Electron Microscope Tomography and Single-particle Reconstruction

Transmission electron microscopy (TEM) can be used to determine the 3D structure of biological samples with the help of techniques such as electron microscope tomography and single-particle reconstruction. While single-particle reconstruction can examine macromolecules and macromolecular complexes in vitro conditions only, tomography permits the study of cell components or small cells in vivo.
Electron Tomography
Electron tomography can be performed either in TEM or STEM (scanning transmission...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Quantifying Trace Metals in Gunflint Microfossils by 3D Correlative X-ray Nanoimaging.

Analytical chemistry·2026

Same author

Spatial Relations between Coccoliths and Their Confining Membrane During Crystal Morphogenesis.

Journal of the American Chemical Society·2026

Same author

Cryo-Correlative Light and X-ray Microscopies: Expanding the Intracellular Chemical Map.

ACS nano·2026

Same author

Self-Supervised Deep-Learning Denoising for X-ray Fluorescence Microscopy with Multi-Element Detectors.

Analytical chemistry·2026

Same author

Genetic Basis of Multiple Antibiotic Resistance of Pathogenic <i>Escherichia coli</i> Strains Isolated from Livestock Complexes in Krasnodar Krai, Russia.

International journal of molecular sciences·2026

Same author

Machine learning approaches to reveal pinealocyte changes in ageing and Alzheimer's disease.

Computers in biology and medicine·2025

Same journal

Denoising algorithm of Φ-OTDR systems based on adaptive fractional wavelet transform denoising.

Optics express·2026

Same journal

Millisecond photon-to-photon latency and high-speed volumetric projection system for optogenetics.

Optics express·2026

Same journal

Polarization-encoded coaxial structured light for high-precision 3D surface profilometry.

Optics express·2026

Same journal

Discrete freeform optical design based on collaborative optimization of point cloud and local normals.

Optics express·2026

Same journal

Ultrafast ghost imaging with 25 GHz speckle switching and wavelength-division multiplexing.

Optics express·2026

Same journal

Atomic vapor cells fabricated by femtosecond laser welding of standard-optical-quality glass.

Optics express·2026

See all related articles

We developed a self-supervised deep learning method for ghost imaging (GI) reconstruction. This approach significantly enhances image quality in noisy conditions without needing clean reference data, improving low-light imaging applications.

Area of Science:

Optics and Photonics
Machine Learning
Image Reconstruction

Background:

Ghost imaging (GI) is an advanced optical imaging technique.
Traditional GI reconstruction methods struggle with noisy data and require clean reference measurements.
Emerging low-light GI applications face significant signal-to-noise ratio challenges.

Purpose of the Study:

To introduce a novel self-supervised deep learning method for GI reconstruction.
To demonstrate significant improvements in reconstruction quality for noisy GI data.
To provide a robust solution for low-light and high-noise GI scenarios.

Main Methods:

Developed a self-supervised deep learning framework for GI.
Utilized a mathematical framework to support the method.

Related Experiment Videos

Validated the approach using both simulated and real synchrotron X-ray GI experimental data.

Main Results:

Achieved superior reconstruction quality compared to existing unsupervised methods, especially in noisy conditions.
Demonstrated effective noise reduction capabilities through self-supervision.
Confirmed the method's efficacy with real-world synchrotron X-ray GI data.

Conclusions:

Self-supervised deep learning offers a powerful, unsupervised approach to GI reconstruction.
The method effectively addresses noise limitations in GI, enabling new applications.
This technique is crucial for advancing micro/nano-scale X-ray imaging and in-vivo/in-operando studies.