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

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

Enhancing graph neural networks through universal self-knowledge distillation.

Neural networks : the official journal of the International Neural Network Society·2025

Same author

3D imaging method based on binary encoded fringes with complementary symmetric error diffusion paths.

Applied optics·2025

Same author

Spatial-temporal binarization encoding basis modulation Fourier single-pixel imaging.

Optics express·2025

Same author

Parameter selection on a multi-exposure fusion method for measuring surfaces with varying reflectivity in microscope fringe projection profilometry.

Applied optics·2024

Same author

Rice's trajectory from wild to domesticated in East Asia.

Science (New York, N.Y.)·2024

Same author

NMSCANet: stereo matching network for speckle variations in single-shot speckle projection profilometry.

Optics express·2024

Same journal

Long-term stabilization of intensity-difference squeezing from four-wave mixing in rubidium vapor.

Optics express·2026

Same journal

Robust 3D topography measurement of large-range high-aspect-ratio structures based on dual-domain statistical filtering in SD-OCT.

Optics express·2026

Same journal

Broadband transmissive terahertz metasurface for simultaneous quad-mode OAM multiplexing.

Optics express·2026

Same journal

Leveraging two-dimensional materials for high-sensitivity optical sensors: quasi-bound states in the continuum within hybrid metasurfaces.

Optics express·2026

Same journal

Resolution investigation for dual-spherical-wave optical scanning holographic microscopy: methods and performance.

Optics express·2026

Same journal

Robustness of parallel subnetwork-filtered diffractive deep neural networks.

Optics express·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 6, 2025

Dual Raster-Scanning Photoacoustic Small-Animal Imager for Vascular Visualization

Dual Raster-Scanning Photoacoustic Small-Animal Imager for Vascular Visualization

Published on: July 15, 2020

SDD-Net: self-supervised dual-domain dual-path single-pixel imaging.

Zhengmin Guo, Pei Zhou, Jiangping Zhu

|November 22, 2024

Summary

This summary is machine-generated.

This study introduces a novel self-supervised single-pixel imaging method that eliminates the need for labeled data, enabling high-fidelity image reconstruction from minimal measurements for complex scenes.

More Related Videos

Lensfree On-chip Tomographic Microscopy Employing Multi-angle Illumination and Pixel Super-resolution

Lensfree On-chip Tomographic Microscopy Employing Multi-angle Illumination and Pixel Super-resolution

Published on: August 16, 2012

Simultaneously Capturing Real-time Images in Two Emission Channels Using a Dual Camera Emission Splitting System: Applications to Cell Adhesion

Simultaneously Capturing Real-time Images in Two Emission Channels Using a Dual Camera Emission Splitting System: Applications to Cell Adhesion

Published on: September 4, 2013

Related Experiment Videos

Last Updated: Jun 6, 2025

Dual Raster-Scanning Photoacoustic Small-Animal Imager for Vascular Visualization

Dual Raster-Scanning Photoacoustic Small-Animal Imager for Vascular Visualization

Published on: July 15, 2020

Lensfree On-chip Tomographic Microscopy Employing Multi-angle Illumination and Pixel Super-resolution

Lensfree On-chip Tomographic Microscopy Employing Multi-angle Illumination and Pixel Super-resolution

Published on: August 16, 2012

Simultaneously Capturing Real-time Images in Two Emission Channels Using a Dual Camera Emission Splitting System: Applications to Cell Adhesion

Simultaneously Capturing Real-time Images in Two Emission Channels Using a Dual Camera Emission Splitting System: Applications to Cell Adhesion

Published on: September 4, 2013

Area of Science:

Optics and Photonics
Computer Vision
Machine Learning

Background:

Supervised deep learning for single-pixel imaging (SPI) requires extensive labeled data, hindering practical applications due to annotation time and limited generalization.
Existing SPI methods struggle with complex scenes and precise imaging details, especially at low sampling rates.

Purpose of the Study:

To develop a self-supervised SPI method that bypasses the need for paired label data, improving efficiency and applicability.
To enhance image reconstruction quality and detail recovery in complex scenarios using a novel network architecture.

Main Methods:

A self-supervised dual-domain, dual-path deep learning network was proposed for single-pixel imaging.
The method utilizes measurement domain and image domain constraints for unique reconstruction.
A structure-texture dual-path network guides the recovery of specific image information.

Main Results:

The proposed method successfully reconstructs detailed information from complex images without labeled data.
High-fidelity images were achieved even with low sampling rate measurements (e.g., 5.45%).
Significant improvements in Peak Signal-to-Noise Ratio (PSNR) by 5.3dB and Structural Similarity Index Measure (SSIM) by 0.23 were observed compared to state-of-the-art methods.

Conclusions:

The self-supervised dual-domain, dual-path SPI method offers superior performance in imaging quality and efficiency.
This approach addresses limitations of supervised methods, enabling practical applications in fields like military and real-time imaging.