Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

The Effects of Allostatic Load on Comorbid Depression-Anxiety Symptoms in Adolescents With Low Family Socioeconomic Status: Evidence From a Cross-Sectional and Cross-Lagged Panel Network Analysis.

Psychophysiology·2026
Same author

Non-suicidal self-injury in middle school students: Influencing factors and a risk prediction model.

Journal of affective disorders·2026
Same author

Convolutional neural network-long short-term memory model combined with Dammann vortex grating for decoding orbital angular momentum shift keying.

Optics letters·2025
Same author

The Impact of Neighborhood and Family Socioeconomic Status on Adolescents' Internalizing Symptoms: The Mediating Role of Pubertal Development Trajectory.

Journal of youth and adolescence·2025
Same author

The double-edged effect of social mobility belief on socioeconomically disadvantaged adolescents' health: The mediating role of intentional self-regulation.

Health psychology : official journal of the Division of Health Psychology, American Psychological Association·2024
Same author

Long-term Neighborhood Poverty Effects on Internalizing Symptoms in Adolescents: Mediated Through Allostatic Load and Pubertal Timing.

The Journal of adolescent health : official publication of the Society for Adolescent Medicine·2023

Related Experiment Video

Updated: Feb 20, 2026

Bringing the Visible Universe into Focus with Robo-AO
10:35

Bringing the Visible Universe into Focus with Robo-AO

Published on: February 12, 2013

20.1K

ViT-SPGD: vision transformer-driven stochastic parallel gradient descent for WFS-less adaptive optics in FSO

Zhaokun Li, Hua Ming, Xiongchao Liu

    Optics Express
    |February 18, 2026
    PubMed
    Summary

    A new method, Vision Transformer-Stochastic Parallel Gradient Descent (ViT-SPGD), enhances free-space optical communication by improving wavefront correction. This hybrid approach accelerates convergence and boosts robustness against atmospheric turbulence.

    More Related Videos

    Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping
    09:43

    Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

    Published on: March 20, 2017

    10.4K
    High-Throughput Total Internal Reflection Fluorescence and Direct Stochastic Optical Reconstruction Microscopy Using a Photonic Chip
    14:09

    High-Throughput Total Internal Reflection Fluorescence and Direct Stochastic Optical Reconstruction Microscopy Using a Photonic Chip

    Published on: November 16, 2019

    7.4K

    Related Experiment Videos

    Last Updated: Feb 20, 2026

    Bringing the Visible Universe into Focus with Robo-AO
    10:35

    Bringing the Visible Universe into Focus with Robo-AO

    Published on: February 12, 2013

    20.1K
    Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping
    09:43

    Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

    Published on: March 20, 2017

    10.4K
    High-Throughput Total Internal Reflection Fluorescence and Direct Stochastic Optical Reconstruction Microscopy Using a Photonic Chip
    14:09

    High-Throughput Total Internal Reflection Fluorescence and Direct Stochastic Optical Reconstruction Microscopy Using a Photonic Chip

    Published on: November 16, 2019

    7.4K

    Area of Science:

    • Optical Engineering
    • Adaptive Optics
    • Machine Learning

    Background:

    • Free-space optical communication (FSOC) relies on adaptive optics (AO) to correct atmospheric turbulence.
    • Conventional wavefront-sensor-less (WFS-less) AO methods like Stochastic Parallel Gradient Descent (SPGD) suffer from slow convergence and local optima, especially with severe aberrations.

    Purpose of the Study:

    • To introduce ViT-SPGD, a novel hybrid method combining Vision Transformer (ViT) and SPGD for improved wavefront correction in WFS-less AO systems.
    • To enhance the speed and accuracy of wavefront distortion correction in FSOC under atmospheric turbulence.

    Main Methods:

    • Developed ViT-SPGD by integrating a Vision Transformer (ViT) for gradient prediction with SPGD for stochastic perturbations.
    • Implemented an adaptive fusion mechanism where ViT guides convergence, while SPGD ensures exploration when ViT confidence is low.
    • Validated performance against SPGD, AdamSPGD, and NSPGD using system-level dynamic simulations.

    Main Results:

    • ViT-SPGD demonstrated substantially accelerated convergence compared to existing methods.
    • The proposed method showed improved robustness in correcting phase distortions caused by atmospheric turbulence.
    • Simulation results confirmed the effectiveness of the hybrid approach in dynamic FSOC scenarios.

    Conclusions:

    • ViT-SPGD offers a significant advancement in wavefront correction for WFS-less AO systems.
    • The integration of deep learning (ViT) with iterative optimization (SPGD) provides a practical solution for high-performance AO.
    • This method paves the way for more reliable and robust FSOC operations in challenging atmospheric conditions.