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

You might also read

Related Articles

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

Sort by
Same author

No One-Size-Fits-All Neurons: Task-based Neurons for Artificial Neural Networks.

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

Heterogeneous neural blind deconvolution: A signal processing-empowered foundation feature extractor for bearing fault diagnosis.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Hyper-Compression: Model Compression via Hyperfunction.

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

Gradient-Refined Federated Learning on Head-Tail Imbalanced Data.

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

Frequency-spatial synergistic network for accelerated multi-contrast MRI reconstruction.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2025
Same author

Boosting Geometric Invariants for Discriminative Forensics of Large-Scale Generated Visual Content.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025

Related Experiment Video

Updated: Jul 27, 2025

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.4K

Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework.

Tingting Wu, Wenna Wu, Ying Yang

    IEEE Transactions on Neural Networks and Learning Systems
    |June 6, 2023
    PubMed
    Summary

    This study introduces a novel Retinex-based framework for low-light image enhancement that simultaneously removes noise. The plug-and-play model offers improved interpretability and outperforms existing methods.

    More Related Videos

    Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis
    07:59

    Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

    Published on: October 28, 2022

    2.8K
    Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
    13:13

    Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

    Published on: March 19, 2021

    3.0K

    Related Experiment Videos

    Last Updated: Jul 27, 2025

    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
    10:39

    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

    Published on: May 24, 2022

    2.4K
    Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis
    07:59

    Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

    Published on: October 28, 2022

    2.8K
    Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
    13:13

    Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

    Published on: March 19, 2021

    3.0K

    Area of Science:

    • Computer Vision
    • Image Processing
    • Artificial Intelligence

    Background:

    • The Retinex model is effective for low-light image enhancement but struggles with noise.
    • Deep learning methods show promise but require extensive labeled data and lack interpretability.

    Purpose of the Study:

    • To develop a Retinex-based framework for simultaneous low-light image enhancement and noise removal.
    • To create a plug-and-play model that integrates a convolutional neural network (CNN) denoiser.
    • To enhance model interpretability for understanding its behavior.

    Main Methods:

    • A sequential Retinex decomposition strategy was employed.
    • A CNN-based denoiser was integrated into a plug-and-play framework to generate a reflectance component.
    • The final image was enhanced using illumination, reflectance, and gamma correction.

    Main Results:

    • The proposed framework effectively enhances low-light images while simultaneously removing noise.
    • The framework demonstrated superior performance compared to state-of-the-art methods across various datasets.
    • The plug-and-play nature of the framework allows for both post hoc and ad hoc interpretability.

    Conclusions:

    • The developed framework offers a robust solution for low-light image enhancement and denoising.
    • The integration of Retinex theory with CNNs provides a more interpretable and effective approach.
    • This method advances the field by addressing limitations of traditional and deep learning-based techniques.