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 Experiment Video

Updated: Jul 26, 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

586

PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN With Dual-Discriminators.

Runmin Cong, Wenyu Yang, Wei Zhang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |June 19, 2023
    PubMed
    Summary

    This study introduces PUGAN, a novel physical model-guided Generative Adversarial Network (GAN) for underwater image enhancement (UIE). PUGAN effectively addresses low contrast and color distortion in underwater images, significantly improving visual quality and downstream task performance.

    Related Concept Videos

    You might also read

    Related Articles

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

    Sort by
    Same author

    CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretation.

    IEEE transactions on medical imaging·2026
    Same author

    Rice-Derived Peptides Exhibit Wound Healing Properties in Human Keratinocytes: Screening, Identification, and Mechanism Revelation.

    Plant foods for human nutrition (Dordrecht, Netherlands)·2026
    Same author

    An Uncertainty-Aware Ensemble Approach to Modeling Utility of Pseudolabels for Semisupervised Learning.

    IEEE transactions on neural networks and learning systems·2026
    Same author

    CuDi: Curve Distillation for Efficient and Controllable Exposure Adjustment.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same author

    Global-Local Interaction and Recalibration Network for Salient Object Detection in Optical Remote Sensing Images.

    IEEE transactions on cybernetics·2026
    Same author

    Association of DNA damage repair related genes with prostate cancer: A multi-omics Mendelian Randomization analysis.

    Medicine·2026

    Area of Science:

    • Computer Vision
    • Image Processing
    • Artificial Intelligence

    Background:

    • Underwater images suffer degradation (low contrast, color distortion, blur) due to light absorption and scattering.
    • This degradation hinders underwater image understanding tasks.
    • Underwater Image Enhancement (UIE) is crucial for improving visual quality.

    Purpose of the Study:

    • To propose a novel physical model-guided Generative Adversarial Network (GAN) for UIE, named PUGAN.
    • To combine the strengths of physical model-based methods and GANs for superior underwater image enhancement.
    • To enhance visual aesthetics and scene adaptability in UIE.

    Main Methods:

    • PUGAN utilizes a GAN architecture with a Parameters Estimation subnetwork (Par-subnet) for physical model inversion.

    More Related Videos

    Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
    09:19

    Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

    Published on: April 18, 2025

    653
    A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry
    06:36

    A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry

    Published on: April 15, 2021

    3.8K

    Related Experiment Videos

    Last Updated: Jul 26, 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

    586
    Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
    09:19

    Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

    Published on: April 18, 2025

    653
    A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry
    06:36

    A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry

    Published on: April 15, 2021

    3.8K
  • A Two-Stream Interaction Enhancement sub-network (TSIE-subnet) incorporates a Degradation Quantization (DQ) module for targeted enhancement.
  • Dual Discriminators are employed for style-content adversarial constraint to ensure authenticity and visual appeal.

    • Main Results:

    • PUGAN demonstrates superior performance over state-of-the-art methods on benchmark datasets.
    • The method achieves significant improvements in both qualitative visual quality and quantitative metrics.
    • Experiments confirm the effectiveness of the Par-subnet, TSIE-subnet, and DQ module.

    Conclusions:

    • PUGAN effectively enhances underwater images by integrating physical models and GANs.
    • The proposed method offers improved visual aesthetics and robustness for UIE.
    • PUGAN represents a significant advancement in underwater image enhancement technology.