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

Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

7.0K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
7.0K

You might also read

Related Articles

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

Sort by
Same author

Mapping climate-conditioned PM<sub>2.5</sub> response under climate change in Taiwan using a high-resolution Geo-AI model.

Journal of environmental management·2026
Same author

Hot Electron-Driven Amide Bond Formation in Plasmonic Nanogaps without Chemical Activation.

The journal of physical chemistry letters·2026
Same author

Cadmium inhibits hSMUG1-mediated uracil excision: quantitative analysis and mitigation by <i>Ganoderma lucidum</i> extracts.

Journal of enzyme inhibition and medicinal chemistry·2026
Same author

DNAJB4/HLJ1 protects against acetaminophen-induced liver injury by attenuating ER stress via HSP70.

Cell biology and toxicology·2026
Same author

Metasurface-Enabled On-Chip Three-Dimensional Optical Manipulation.

ACS nano·2026
Same author

High-<i>Q</i> Metasurface Absorber Enabled by Symmetry Breaking in a Plasmonic Lattice.

Nano letters·2026
Same journal

Correction to "Living Therapeutic Microneedles Integrated with Built-In Metabolic Engines for Autonomous Diabetic Wound Management".

Nano letters·2026
Same journal

Chiral Quasi-Bound States in the Continuum on the Verge of the Light Cone.

Nano letters·2026
Same journal

Scalable Atomically Interfaced Heterostructure Photoelectrodes for Broadband Solar Energy Harvesting and Stable Li-Ion Storage.

Nano letters·2026
Same journal

Bulk and Surface Excitons in the van der Waals Magnet CrSBr: Magneto-Optical Studies to 55 T.

Nano letters·2026
Same journal

High-Entropy Alloy Nanomaterials with Well-Designed Nanostructures for Electrocatalytic Applications.

Nano letters·2026
Same journal

Symmetrical Tetravalent Aptamer-Protein Conjugate with Ultrahigh <i>In Vivo</i> Stability for Targeted Cancer Imaging and Therapy.

Nano letters·2026
See all related articles

Related Experiment Video

Updated: Jul 11, 2025

Lensfree On-chip Tomographic Microscopy Employing Multi-angle Illumination and Pixel Super-resolution
08:41

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

Published on: August 16, 2012

11.6K

High-Resolution Metalens Imaging with Sequential Artificial Intelligence Models.

Wei-Lun Hsu1, Chen-Fu Huang1, Chih-Chun Tan1

  • 1Department of Optics and Photonics, National Central University, Taoyuan, 320371, Taiwan.

Nano Letters
|November 8, 2023
PubMed
Summary
This summary is machine-generated.

This study integrates Gallium Nitride (GaN) metalenses with artificial intelligence (AI) models to fix image blurriness and color cast. The AI successfully corrected optical loss issues, enhancing full-color metalens imaging systems.

Keywords:
artificial intelligence modelsfull-color imagingimage reconstructionmetalens

More Related Videos

Rapid Acquisition of 3D Images Using High-resolution Episcopic Microscopy
07:27

Rapid Acquisition of 3D Images Using High-resolution Episcopic Microscopy

Published on: November 21, 2016

7.7K
Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling
10:45

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Published on: May 31, 2017

13.1K

Related Experiment Videos

Last Updated: Jul 11, 2025

Lensfree On-chip Tomographic Microscopy Employing Multi-angle Illumination and Pixel Super-resolution
08:41

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

Published on: August 16, 2012

11.6K
Rapid Acquisition of 3D Images Using High-resolution Episcopic Microscopy
07:27

Rapid Acquisition of 3D Images Using High-resolution Episcopic Microscopy

Published on: November 21, 2016

7.7K
Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling
10:45

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Published on: May 31, 2017

13.1K

Area of Science:

  • Optics and Photonics
  • Artificial Intelligence
  • Image Processing

Background:

  • Gallium Nitride (GaN)-based metalenses offer advanced optical functionalities but can suffer from color cast due to optical loss, particularly in the blue spectral range.
  • Image quality issues like blurriness and color cast can degrade the performance of metalens-based imaging systems.
  • Existing image correction methods may not fully address the specific challenges posed by metalens optical properties.

Purpose of the Study:

  • To analyze the optical response of a GaN-based metalens and identify causes of image degradation.
  • To develop and implement sequential artificial intelligence (AI) models for correcting color cast and reconstructing image details.
  • To evaluate the effectiveness of the integrated metalens and AI system in improving full-color imaging performance.

Main Methods:

  • Optical response analysis of a GaN-based metalens.
  • Application of sequential Autoencoder and CodeFormer AI models for image restoration.
  • Correction of color cast and image detail reconstruction using AI.
  • Numerical validation using CIE 1931 chromaticity diagrams and peak signal-to-noise ratio (PSNR) analysis.

Main Results:

  • Optical loss in the blue spectral range was identified as the cause of color cast in metalens images.
  • Sequential Autoencoder and CodeFormer models effectively corrected color cast and reconstructed image details for various face image categories.
  • AI models demonstrated image repair capabilities even without blue spectral information.
  • CIE 1931 chromaticity diagrams and PSNR analysis confirmed the significant improvement in image quality.

Conclusions:

  • The integration of GaN metalenses with sequential AI models (Autoencoder and CodeFormer) successfully overcomes image quality limitations like color cast and blurriness.
  • This hybrid approach represents a significant advancement in enhancing the performance and practical application of full-color metalens imaging systems.
  • The AI models' ability to restore images even with missing spectral information highlights their robustness and potential for diverse imaging applications.