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: Oct 20, 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

699

Layout-to-Image Translation With Double Pooling Generative Adversarial Networks.

Hao Tang, Nicu Sebe

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |September 15, 2021
    PubMed
    Summary

    This study introduces Double Pooling GAN (DPGAN) to improve layout-to-image translation by enhancing semantic consistency. The novel Double Pooling Module (DPM) captures both short and long-range dependencies for more realistic image generation.

    Related Concept Videos

    Improving Translational Accuracy02:07

    Improving Translational Accuracy

    3.1K
    3.1K

    You might also read

    Related Articles

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

    Sort by
    Same author

    Using functional magnetic resonance imaging to evaluate an acute allograft rejection model in rats.

    Magnetic resonance imaging·2019
    Same author

    QsvR integrates into quorum sensing circuit to control Vibrio parahaemolyticus virulence.

    Environmental microbiology·2019
    Same author

    mi R -15a/15b Cluster Modulates Survival of Mesenchymal Stem Cells to Improve Its Therapeutic Efficacy of Myocardial Infarction.

    Journal of the American Heart Association·2019
    Same author

    Retrospective analysis of Clostridium difficile infection in patients with ulcerative colitis in a tertiary hospital in China.

    BMC gastroenterology·2019
    Same author

    CCCH-type zinc finger antiviral protein is specifically overexpressed in spleen in response to subgroup J avian leukosis virus infection in chicken.

    Research in veterinary science·2018
    Same author

    Mapping Twisted Light into and out of a Photonic Chip.

    Physical review letters·2018

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Layout-to-image translation aims to generate realistic images from semantic layouts.
    • Existing methods struggle with semantic constraints, leading to inconsistent and unrealistic outputs.
    • Lack of effective semantic understanding causes models to ignore object-specific dependencies.

    Purpose of the Study:

    • To propose a novel Double Pooling GAN (DPGAN) for improved layout-to-image translation.
    • To enhance semantic consistency and preserve information during image generation.
    • To address the limitations of existing methods in capturing semantic dependencies.

    Main Methods:

    • Introduced a novel Double Pooling Module (DPM) comprising Square-shape Pooling Module (SPM) and Rectangle-shape Pooling Module (RPM).

    More Related Videos

    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
    04:17

    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

    Published on: May 10, 2024

    1.0K

    Related Experiment Videos

    Last Updated: Oct 20, 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

    699
    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
    04:17

    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

    Published on: May 10, 2024

    1.0K
  • SPM captures short-range semantic dependencies at various spatial scales.
  • RPM captures long-range semantic dependencies horizontally and vertically, fusing both for an enlarged receptive field.

    • Main Results:

    • DPGAN achieves state-of-the-art results on five popular datasets.
    • The proposed method generates photo-realistic and semantically consistent images.
    • Demonstrated superior performance compared to existing layout-to-image translation techniques.

    Conclusions:

    • DPGAN effectively addresses the challenge of semantic constraints in image translation.
    • The DPM is a versatile module that can enhance feature representation in GANs.
    • The proposed approach offers a significant advancement in generating semantically accurate images from layouts.