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

12.3K
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...
12.3K

You might also read

Related Articles

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

Sort by
Same author

MSIA-Net: A Lightweight Infrared Target Detection Network with Efficient Information Fusion.

Entropy (Basel, Switzerland)·2023
Same author

Transformer-Based Model with Dynamic Attention Pyramid Head for Semantic Segmentation of VHR Remote Sensing Imagery.

Entropy (Basel, Switzerland)·2022
Same author

BRefine: Achieving High-Quality Instance Segmentation.

Sensors (Basel, Switzerland)·2022
See all related articles

Related Experiment Video

Updated: May 6, 2026

Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm
06:53

Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm

Published on: July 23, 2020

5.6K

Ref-MEF: Reference-Guided Flexible Gated Image Reconstruction Network for Multi-Exposure Image Fusion.

Yuhui Huang1, Shangbo Zhou1, Yufen Xu1

  • 1College of Computer Science, Chongqing University, Chongqing 400044, China.

Entropy (Basel, Switzerland)
|February 23, 2024
PubMed
Summary

Ref-MEF is a novel reference-guided method for multi-exposure image fusion (MEF) that handles varying input numbers. It produces high-quality, detailed images efficiently, outperforming existing approaches.

Keywords:
computational photographyconvolutional neural networksimage processingmulti-exposure fusion

More Related Videos

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.1K
Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

353

Related Experiment Videos

Last Updated: May 6, 2026

Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm
06:53

Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm

Published on: July 23, 2020

5.6K
Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.1K
Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

353

Area of Science:

  • Computer Vision
  • Image Processing
  • Artificial Intelligence

Background:

  • Multi-exposure image fusion (MEF) combines images with different exposures into one high-quality image.
  • Deep learning MEF methods struggle with dynamic input numbers due to rigid network structures.

Purpose of the Study:

  • To introduce Ref-MEF, a reference-guided MEF method adaptable to an uncertain number of input images.
  • To address the limitations of existing deep learning MEF techniques in handling variable inputs.

Main Methods:

  • Developed a reference-guided exposure correction (REC) module using channel and spatial attention.
  • Implemented an exposure-guided feature fusion (EGFF) module with Gaussian filter weights.
  • Utilized a gated context aggregation network (GCAN) and global residual learning (GRL) for image reconstruction.
  • Incorporated a refined loss function with gradient fidelity.

Main Results:

  • Ref-MEF successfully fuses multiple exposures into a single, high-quality image.
  • The method demonstrates superior performance in image feature evaluations and holistic assessments.
  • Achieved notable computational efficiency, especially as the number of input images increases.

Conclusions:

  • Ref-MEF offers a robust solution for multi-exposure image fusion with an uncertain number of inputs.
  • The proposed method enhances image detail and visual quality while maintaining computational efficiency.
  • Ref-MEF represents a significant advancement in deep learning-based image fusion techniques.