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

6.9K
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...
6.9K

You might also read

Related Articles

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

Sort by
Same author

Two-year-supervised resistance training prevented diabetes incidence in people with prediabetes: A randomised control trial.

Diabetes/metabolism research and reviews·2019
Same author

Preliminary evaluation of a predictive controller for a rotary blood pump based on pulmonary oxygen gas exchange.

Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine·2019
Same author

A Destructive New Disease of Citrus in China Caused by Cryptosporiopsis citricarpa sp. nov.

Plant disease·2019
Same author

Effects of membrane reference state on shape memory of a red blood cell.

Computer methods in biomechanics and biomedical engineering·2019
Same author

Ultrafast Photovoltaic-Type Deep Ultraviolet Photodetectors Using Hybrid Zero-/Two-Dimensional Heterojunctions.

ACS applied materials & interfaces·2019
Same author

Phenolic profile and antioxidant properties of sand rice (Agriophyllum squarrosum) as affected by cooking and in vitro digestion.

Journal of the science of food and agriculture·2019

Related Experiment Video

Updated: Jun 2, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

463

Feature enhanced cascading attention network for lightweight image super-resolution.

Feng Huang1, Hongwei Liu1, Liqiong Chen1

  • 1College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, 350108, China.

Scientific Reports
|January 15, 2025
PubMed
Summary

We developed a Feature Enhanced Cascading Attention Network (FECAN) for efficient image super-resolution (SR). FECAN improves visual quality and reduces computational costs, outperforming other lightweight SR models.

Keywords:
Convolution neural networkEnhanced shuffle attentionLightweight image super-resolutionMulti-scale large separable kernel attention

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

366
Super-resolution Imaging of Neuronal Dense-core Vesicles
09:30

Super-resolution Imaging of Neuronal Dense-core Vesicles

Published on: July 2, 2014

9.7K

Related Experiment Videos

Last Updated: Jun 2, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

463
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

366
Super-resolution Imaging of Neuronal Dense-core Vesicles
09:30

Super-resolution Imaging of Neuronal Dense-core Vesicles

Published on: July 2, 2014

9.7K

Area of Science:

  • Computer Vision
  • Deep Learning
  • Image Processing

Background:

  • Attention mechanisms enhance image restoration by capturing feature dependencies.
  • Existing methods face limitations in perceptual capabilities and efficiency for low-power devices.

Purpose of the Study:

  • To propose a novel Feature Enhanced Cascading Attention Network (FECAN) for efficient and high-performance image super-resolution (SR).
  • To address the limitations of current attention mechanisms in perceptual quality and computational cost.

Main Methods:

  • Introduced a Feature Enhanced Cascading Attention (FECA) mechanism, comprising Enhanced Shuffle Attention (ESA) and Multi-Scale Large Separable Kernel Attention (MLSKA).
  • ESA enhances high-frequency texture features, while MLSKA performs further extraction and fusion of multi-scale information.
  • Evaluated FECAN's effectiveness by varying the number of High-Frequency Enhancement Modules (HFEM) within the network.

Main Results:

  • FECAN demonstrated superior performance over state-of-the-art lightweight SR networks in objective metrics and subjective visual quality.
  • At 4x scale with a 121K model size, FECAN achieved a 0.07 dB PSNR improvement over MAN-tiny.
  • FECAN reduced network parameters by ~19% and FLOPs by ~20% compared to MAN-tiny.

Conclusions:

  • FECAN offers an improved trade-off between super-resolution performance and model complexity.
  • The proposed FECA mechanism effectively extracts and fuses rich, fine-grained high-frequency information for enhanced SR.
  • FECAN is suitable for low-power devices requiring high-quality image restoration.