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: Dec 11, 2025

Using Generative Art to Convey Past and Future Climate Transitions
06:10

Using Generative Art to Convey Past and Future Climate Transitions

Published on: March 31, 2023

1.3K

Cantonese Porcelain Image Generation Using User-Guided Generative Adversarial Networks.

Steven Szu-Chi Chen, Hui Cui, Peng Tan

    IEEE Computer Graphics and Applications
    |August 25, 2020
    PubMed
    Summary
    This summary is machine-generated.

    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

    A Review of Cybersecurity Issues in Smart Meter-Based Energy Trading.

    Sensors (Basel, Switzerland)·2026
    Same author

    From Prediction to Insight: Visual Analytics for Understanding Compound Potency Models.

    IEEE computer graphics and applications·2026
    Same author

    Multi-granularity transformer contrastive learning and feature reconstruction for prediction of disease-related miRNAs.

    BMC bioinformatics·2026
    Same author

    The Impact of Nursing Education Innovation on the Quality of Care for Elderly Hospitalized Patients: A Systematic Review Based on Student Competency Development.

    Journal of multidisciplinary healthcare·2026
    Same author

    Leveraging Social Interaction: Stroke Rehabilitation Using Extended Reality.

    IEEE computer graphics and applications·2026
    Same author

    Precise estimation of tissue microstructure with hybrid graph transformer.

    Artificial intelligence in medicine·2026

    This study introduces an intelligent generative adversarial network (GAN) system for creating Cantonese porcelain-styled images from masks. The novel approach enhances details and contrast, overcoming challenges with small datasets and complex art styles.

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Digital Art

    Background:

    • Generative Adversarial Networks (GANs) have advanced automated image style transfer.
    • Synthesizing detailed images from masks, especially for specific art styles like Cantonese porcelain, is challenging with limited data.

    Purpose of the Study:

    • To develop an intelligent GAN-based system for generating Cantonese porcelain-styled images from user-defined masks.
    • To enhance synthesized images with local details and improved contrast by incorporating user intent and prior knowledge.

    Main Methods:

    • A GAN-based system utilizing user-defined masks to generate initial natural images.
    • A semantic user intent enhancement module to retrieve relevant images and refine local patterns.
    • Style transfer to render the refined image in the Cantonese porcelain aesthetic.

    Related Experiment Videos

    Last Updated: Dec 11, 2025

    Using Generative Art to Convey Past and Future Climate Transitions
    06:10

    Using Generative Art to Convey Past and Future Climate Transitions

    Published on: March 31, 2023

    1.3K

    Main Results:

    • The system successfully generates synthesized images from masks, preserving detailed patterns.
    • Incorporation of semantic user intent improved local details and contrast in the final styled images.
    • Experimental results and ablation studies validated the effectiveness of the proposed enhancement modules.

    Conclusions:

    • The proposed intelligent GAN system effectively addresses the challenge of generating detailed, styled images from masks.
    • The semantic user intent enhancement module is crucial for improving image quality and detail preservation.
    • This method offers a novel approach to automated image style transfer for specific artistic styles.