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 Video

Updated: Feb 16, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Deep-learning-based ghost imaging.

Meng Lyu^1,2, Wei Wang^3,4, Hao Wang^1,2

¹Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Shanghai, 201800, China.

Scientific Reports

|December 21, 2017

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Computed tomography imaging and observation of hemorrhage in traumatic splenic rupture pre and post partial splenectomy.

Biomedizinische Technik. Biomedical engineering·2026

Same author

Association between estimated pulse wave velocity and acute kidney injury in critically ill sepsis patients: A MIMIC-IV database analysis.

Medicine·2026

Same author

Metasurface-assisted spatial light modulation with a large field of view.

Applied optics·2026

Same author

Comparative efficacy and safety of carboplatin-based versus cisplatin-based chemotherapy in muscle-invasive and advanced bladder cancer: A systematic review and meta-analysis.

European journal of clinical pharmacology·2026

Same author

Postoperative stimulated thyroglobulin and the ps-tg/TSH ratio enhance the 2025 ATA risk stratification for predicting radioiodine response in papillary thyroid carcinoma.

Annals of medicine·2026

Same author

Effects and Mechanisms of Stevioside on Metabolic Dysfunction-Associated Steatotic Liver Disease.

Food science & nutrition·2026

Same journal

Serum vitamin D level and its association with vertigo frequency and severity in Meniere disease.

Scientific reports·2026

Same journal

PFA-Net: a physics-informed feature enhancement and attention network for interpretable bearing fault diagnosis under strong noise.

Scientific reports·2026

Same journal

Circulating inflammatory, redox, and apoptosis-related alterations in drug-naive idiopathic pulmonary fibrosis: an exploratory case-control study.

Scientific reports·2026

Same journal

A baseline-oriented dynamic aggregation approach for demand-side heterogeneous controllable resources.

Scientific reports·2026

Same journal

Temporal precision and accuracy in schizophrenia: an exploratory study.

Scientific reports·2026

Same journal

Prefrontal EEG spectral and nonlinear signatures of subthreshold depression during resting state and affectively valenced picture/video viewing: a participant-level analysis.

Scientific reports·2026

See all related articles

We introduce ghost imaging using deep learning (GIDL), a new computational ghost imaging method. GIDL significantly enhances image reconstruction quality, especially at low sampling rates, outperforming traditional techniques.

Area of Science:

Computational imaging
Deep learning applications
Optical physics

Background:

Traditional ghost imaging (GI) methods face limitations in image quality and sampling efficiency.
Deep learning offers potential for improving computational imaging reconstruction.
Developing efficient imaging techniques is crucial for various scientific and industrial applications.

Purpose of the Study:

To propose and demonstrate a novel framework for computational ghost imaging using deep learning (GIDL).
To enhance image reconstruction quality in ghost imaging.
To evaluate GIDL performance, particularly at extremely low sampling rates.

Main Methods:

Training a deep neural network using traditional GI reconstructed images and their ground-truth counterparts.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Feb 16, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Developing a GIDL framework to learn the sensing model for improved reconstruction.

Conducting numerical simulations and optical experiments for validation.

Main Results:

The proposed GIDL framework significantly improves image reconstruction quality compared to traditional GI.
GIDL demonstrates superior performance over compressive sensing at extremely low sampling rates.
Successful demonstration of GIDL through both numerical simulations and optical experiments.

Conclusions:

GIDL represents a novel and effective approach to computational ghost imaging.
Deep learning integration enhances ghost imaging capabilities, particularly in data-scarce scenarios.
The proposed method offers a promising direction for future advancements in computational imaging.