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

Deconvolution01:20

Deconvolution

168
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
168

You might also read

Related Articles

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

Sort by
Same author

Aberrant expression of microRNA-132-3p and microRNA-146a-5p in Parkinson's disease patients.

Open life sciences·2021
Same author

Mass Spectrometry-Based Shotgun Lipidomics for Cancer Research.

Advances in experimental medicine and biology·2021
Same author

A Role for Transmembrane Protein 16C/Slack Impairment in Excitatory Nociceptive Synaptic Plasticity in the Pathogenesis of Remifentanil-induced Hyperalgesia in Rats.

Neuroscience bulletin·2021
Same author

Hydrogen enriched saline alleviates morphine tolerance via inhibiting neuroinflammation, GLT-1, GS nitration and NMDA receptor trafficking and functioning in the spinal cord of rats.

Neuroscience letters·2021
Same author

Urban Air Pollution Mapping Using Fleet Vehicles as Mobile Monitors and Machine Learning.

Environmental science & technology·2021
Same author

A conserved immunogenic and vulnerable site on the coronavirus spike protein delineated by cross-reactive monoclonal antibodies.

Nature communications·2021

Related Experiment Video

Updated: Jul 13, 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

568

Multi-Scale Attention Feature Enhancement Network for Single Image Dehazing.

Weida Dong1,2, Chunyan Wang1, Hao Sun1

  • 1School of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, China.

Sensors (Basel, Switzerland)
|October 14, 2023
PubMed
Summary

This study introduces a novel image dehazing network that enhances multi-scale features to prevent color distortion and detail loss. The proposed method effectively removes haze while preserving image color and details, outperforming existing algorithms.

Keywords:
color fidelityfeature enhancementimage dehazingimage restoration

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

439
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Related Experiment Videos

Last Updated: Jul 13, 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

568
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

439
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Area of Science:

  • Computer Vision
  • Image Processing
  • Artificial Intelligence

Background:

  • Existing image dehazing algorithms often suffer from color distortion and loss of fine details.
  • Developing effective dehazing methods is crucial for various applications like autonomous driving and surveillance.

Purpose of the Study:

  • To propose an end-to-end image dehazing network that addresses color distortion and detail loss.
  • To enhance multi-scale feature representation for improved haze removal.
  • To preserve original image color fidelity and intricate details.

Main Methods:

  • An end-to-end network incorporating a feature extraction enhancement module to capture details and expand receptive fields.
  • Utilizing channel and pixel attention mechanisms within a feature fusion enhancement module for dynamic weight adjustment.
  • Employing a context enhancement module to refine semantic information and suppress noise for accurate haze density estimation.

Main Results:

  • Achieved a PSNR score of 33.74, SSIM of 0.9843, and LPIPS distance of 0.0040 on the SOTS-outdoor dataset.
  • Demonstrated superior dehazing performance compared to representative methods on synthetic hazy images.
  • Showcased effective haze removal with preserved details and color fidelity on real-world hazy images.

Conclusions:

  • The proposed multi-scale feature enhancement network effectively removes haze while preserving image color and details.
  • The method offers significant advantages over existing dehazing techniques, particularly in maintaining image quality.
  • The network's ability to handle both synthetic and real-world hazy images highlights its practical applicability.