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

Transformers01:26

Transformers

1.1K
A device that transforms voltages from one value to another using induction is called a transformer. A transformer consists of two separate coils, or windings, wrapped around the same soft iron core. However, they are electrically insulated from each other.
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
1.1K
Attenuated Total Reflectance (ATR) Infrared Spectroscopy: Overview01:13

Attenuated Total Reflectance (ATR) Infrared Spectroscopy: Overview

447
Attenuated total reflectance (ATR) infrared spectroscopy is a powerful analytical technique used to study the composition of materials. It is widely employed in chemistry, materials science, forensic science, and other fields where sample characterization is required. ATR has several advantages over traditional transmission IR spectroscopy, including the requirement of little to no sample preparation and the ability to analyze a wide range of samples.
The ATR process begins by directing a beam...
447

You might also read

Related Articles

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

Sort by
Same author

Low body mass index is related to post-lumbar puncture headache in Chinese adults: A cross-sectional study.

The Journal of international medical research·2026
Same author

RCTUnet: a deep learning model for crop-residue-soil image segmentation and crop residue cover extraction.

Journal of Zhejiang University. Science. B·2026
Same author

Corrective osteotomy for distal radius malunion using 3D-printed patient-specific guides and spacers: a retrospective comparative study.

BMC musculoskeletal disorders·2026
Same author

CornPheno: Phenotyping corn ear kernels in the wild via point query transformer.

Plant phenomics (Washington, D.C.)·2026
Same author

Gelsolin-3: A Novel Myelin Autoantigen in Demyelinating Guillain-Barré Syndrome.

Annals of neurology·2026
Same author

Incidence and outcome of major perinatal comorbidities of all hospitalized neonates requiring intensive and critical care: a livebirth population-based survey.

The journal of maternal-fetal & neonatal medicine : the official journal of the European Association of Perinatal Medicine, the Federation of Asia and Oceania Perinatal Societies, the International Society of Perinatal Obstetricians·2026

Related Experiment Video

Updated: Aug 7, 2025

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.5K

HMFT: Hyperspectral and Multispectral Image Fusion Super-Resolution Method Based on Efficient Transformer and

Baojun Qiao1, Binghui Xu1, Yi Xie1

  • 1Henan Key Laboratory of Big Data Analysis and Processing, School of Computer and Information Engineering, Henan University, Kaifeng 475000, China.

Computational Intelligence and Neuroscience
|March 13, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces a novel Transformer-based network for hyperspectral image super-resolution. The hybrid approach effectively fuses low-resolution hyperspectral images with high-resolution multispectral images, achieving superior results.

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

471
Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
07:34

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.1K

Related Experiment Videos

Last Updated: Aug 7, 2025

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.5K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

471
Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
07:34

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.1K

Area of Science:

  • Remote Sensing
  • Computer Vision
  • Image Processing

Background:

  • Hyperspectral images (HSIs) suffer from low spatial resolution due to imaging mechanisms.
  • Fusion of low-resolution HSI (LR-HSI) with high-resolution multispectral images (HR-MSI) is crucial for generating high-resolution HSI (HR-HSI).
  • Current state-of-the-art methods primarily rely on Convolutional Neural Networks (CNNs), with limited exploration of Transformer architectures.

Purpose of the Study:

  • To propose a novel, efficient hybrid network architecture for hyperspectral image super-resolution using Transformer.
  • To leverage the strengths of both convolutional and Transformer components for enhanced spatial-spectral information extraction.
  • To improve the efficiency and reduce the computational complexity of hyperspectral image super-resolution models.

Main Methods:

  • A hybrid CNN-Transformer backbone is developed to extract spatial-spectral information, utilizing local and global feature extraction capabilities.
  • A convolutional attention mechanism is incorporated to refine features in spatial and spectral dimensions, focusing on high-frequency information and spectral correlations.
  • A feature split module (FSM) replaces native Transformer self-attention to manage large HSI resolutions, reducing computational complexity and memory footprint.

Main Results:

  • The proposed network demonstrates superior performance in qualitative and quantitative evaluations compared to existing state-of-the-art methods.
  • The hybrid architecture effectively captures both local and global dependencies for improved image reconstruction.
  • The feature split module significantly enhances training efficiency for large-scale hyperspectral datasets.

Conclusions:

  • The developed hybrid CNN-Transformer network offers an effective and efficient solution for hyperspectral image super-resolution.
  • The integration of convolutional attention and the feature split module are key innovations for improving performance and efficiency.
  • This approach advances the field of hyperspectral image fusion and super-resolution, paving the way for more sophisticated remote sensing applications.