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

Large-scale quantum communication networks with integrated photonics.

Nature·2026
Same author

Entanglement-controlled vectorial meta-holography.

Light, science & applications·2025
Same author

Complementary Superwetting Structures Treated by a Femtosecond Laser for Simultaneous Spontaneous Directional Transport of Water Droplets and Underwater Bubbles.

Langmuir : the ACS journal of surfaces and colloids·2024
Same author

Demonstration of hypergraph-state quantum information processing.

Nature communications·2024
Same author

Fractal photonic anomalous Floquet topological insulators to generate multiple quantum chiral edge states.

Light, science & applications·2023
Same author

Droplet-Driven Self-Propelled Devices Fabricated by a Femtosecond Laser.

ACS applied materials & interfaces·2023
Same journal

Nanozyme-Reinforced miR-197-3p Delivery Resets Metabolic and Senescence Pathways to Rejuvenate Osteoarthritic Cartilage.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same journal

Correction to "Nanoparticles (NPs)-Meditated LncRNA AFAP1-AS1 Silencing to Block Wnt/β-Catenin Signaling Pathway for Synergistic Reversal of Radioresistance and Effective Cancer Radiotherapy".

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same journal

Femtosecond-Laser Nanocavitation Regenerates SERS-Active Plasmonic Nanogaps for Longitudinal Molecular Sensing at Biointerfaces.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same journal

Correction to "Bioinspired Polyacrylic Acid-Based Dressing: Wet Adhesive, Self-Healing, and Multi-Biofunctional Coacervate Hydrogel Accelerates Wound Healing".

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same journal

Non-Line-of-Sight Passive Ammonia Sensor Loaded With MXene/In<sub>2</sub>O<sub>3</sub> Composites for Agricultural Products Quality Deterioration Detection.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same journal

Cerium Nanoparticle-Mediated Inhibition of the NSUN2/m<sup>5</sup>C Axis Suppresses Synovial Aggression in Rheumatoid Arthritis.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
See all related articles

Related Experiment Video

Updated: Sep 13, 2025

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

10.0K

High-Speed Design of Multiplexed Meta-Optics Enabled by Physics-Driven Self-Supervised Network.

Yuqing He1, Sheng Ye1, Yue Han1

  • 1State Key Laboratory for Mesoscopic Physics and Frontiers Science Center for Nano-optoelectronics & Collaborative Innovation Center of Quantum Matter, School of Physics, Peking University, Beijing, 100871, China.

Advanced Science (Weinheim, Baden-Wurttemberg, Germany)
|July 31, 2025
PubMed
Summary
This summary is machine-generated.

Artificial intelligence (AI) accelerates meta-optics design. A novel physics-driven self-supervised network (PDSS-Net) enables iteration-free design of meta-holograms, reducing computation time by over 1000-fold.

Keywords:
artificial intelligencehigh‐speed designmeta‐holographymultiplexed meta‐opticsself‐supervised learning

More Related Videos

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms
08:48

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

Published on: September 25, 2020

5.8K
Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.4K

Related Experiment Videos

Last Updated: Sep 13, 2025

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

10.0K
Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms
08:48

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

Published on: September 25, 2020

5.8K
Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.4K

Area of Science:

  • Optics and Photonics
  • Artificial Intelligence
  • Materials Science

Background:

  • Artificial intelligence (AI) accelerates meta-optics design by predicting meta-atom transmission coefficients.
  • Conventional metasurface design, especially for meta-holography, requires extensive optimization iterations, leading to long computation times.
  • Modifying target images in meta-holography necessitates repeating the entire design process.

Purpose of the Study:

  • To develop an AI-assisted framework that significantly expedites the design process for meta-holography and other metasurface applications.
  • To introduce a physics-driven self-supervised network (PDSS-Net) capable of iteration-free inference.
  • To demonstrate the network's adaptability for complex, multiplexed meta-holograms.

Main Methods:

  • Proposed a physics-driven self-supervised network (PDSS-Net) incorporating an encoder-decoder module.
  • Trained the network to establish a mapping between input holographic images and output meta-atom structural parameters.
  • Validated the network's performance on designing 2K-resolution, three-wavelength-multiplexed meta-holograms and complex multiplexed scalar/vectorial meta-holograms.

Main Results:

  • Achieved iteration-free inference for meta-hologram design after self-supervised training.
  • Completed the design of 2K-resolution, three-wavelength-multiplexed meta-holograms in under one second.
  • Demonstrated a computational speedup exceeding 1000-fold compared to conventional optimization methods.
  • Successfully designed wavelength-polarization-depth multiplexed scalar and vectorial meta-holograms through retraining.

Conclusions:

  • The PDSS-Net offers an iteration-free computational paradigm for meta-optics design.
  • This approach significantly accelerates the design of multifunctional metasurfaces, including complex meta-holograms.
  • The developed method facilitates the large-scale application of meta-devices by enabling rapid, adaptable intelligent design.