Jove
Visualize
Contact Us

Related Concept Videos

Deconvolution01:20

Deconvolution

271
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...
271
Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

8.3K
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...
8.3K

You might also read

Related Articles

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

Sort by
Same author

Local Adaptive Image Filtering Based on Recursive Dilation Segmentation.

Sensors (Basel, Switzerland)·2023
Same author

Robust RGB-T Tracking via Graph Attention-Based Bilinear Pooling.

IEEE transactions on neural networks and learning systems·2022
Same author

A Review of Remote Sensing Image Dehazing.

Sensors (Basel, Switzerland)·2021
Same author

IDE: Image Dehazing and Exposure Using an Enhanced Atmospheric Scattering Model.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021
Same author

JsrNet: A Joint Sampling-Reconstruction Framework for Distributed Compressive Video Sensing.

Sensors (Basel, Switzerland)·2020
Same author

IDGCP: Image Dehazing Based on Gamma Correction Prior.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2019
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 Experiment Video

Updated: Sep 29, 2025

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
10:16

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

12.4K

High-Resolution Representations Network for Single Image Dehazing.

Wensheng Han1, Hong Zhu1, Chenghui Qi2

  • 1School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China.

Sensors (Basel, Switzerland)
|March 26, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces DeHRNet, a novel deep learning model for image dehazing. DeHRNet enhances high-resolution feature preservation, leading to more natural-looking restored images and outperforming existing methods.

Keywords:
deep learninghigh-resolution representationsimage dehazingimage restoration

More Related Videos

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

665
Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
07:15

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

558

Related Experiment Videos

Last Updated: Sep 29, 2025

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
10:16

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

12.4K
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

665
Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
07:15

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

558

Area of Science:

  • Computer Vision
  • Deep Learning
  • Image Processing

Background:

  • Deep learning image dehazing methods face challenges with parameter estimation and spatial information preservation.
  • Existing U-Net-based architectures struggle to maintain high-resolution details during the dehazing process.

Purpose of the Study:

  • To propose a novel image dehazing network, DeHRNet, that addresses limitations in current deep learning approaches.
  • To improve the accuracy of parameter estimation and enhance the preservation of spatial information in hazy images.

Main Methods:

  • A modified High-Resolution Network (HRNet) architecture, named DeHRNet, is developed for image dehazing.
  • A new network stage is introduced to aggregate feature maps from all branches via up-sampling, enhancing high-resolution representations.
  • The modified HRNet, originally for human pose estimation, is adapted for the image dehazing task.

Main Results:

  • DeHRNet demonstrates superior performance compared to existing dehazing methods on both synthesized and natural hazy images.
  • The enhanced high-resolution representations contribute to generating more natural and visually appealing restored images.
  • Experimental results validate the effectiveness of the proposed network modifications for image dehazing.

Conclusions:

  • DeHRNet offers an effective solution for image dehazing by leveraging and modifying the HRNet architecture.
  • The proposed modifications successfully enhance the preservation of spatial information and improve the naturalness of dehazed images.
  • DeHRNet represents a significant advancement in deep learning-based image dehazing techniques.