Dual stage augmented colorful texture synthesis from hand sketch

Jinxuan Liu, Junyu Dong, Shu Zhang, Tingge Zhang, Ying Gao, Hui Yu

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    197 Downloads (Pure)

    Abstract

    In this paper, we investigate the texture synthesis method generated from the hand-made sketches. In recent years, GANs have been vigorously studied in the field of image generation, yet the texture synthesis from the hand sketch has not been extensively studied. In order to enable the synthesized image not only possesses the texture features, but also the vibrant color, we propose a cascaded network model that generates a texture image through a dual-stage network. The proposed framework firstly generates a grayscale image with basic texture properties from hand sketch based on the conditional GANs. This grayscale texture is then colorized in the second stage. The network in the second stage is pre-trained using our constructed dataset to learn how to translate the grayscale image to a colorful image. This paper aims to design a new network to generate realistic texture from hand sketch. A series of experiments are conducted to validate the effectiveness of our method. Encouraging results are achieved. The experimental results demonstrate that our dual stage model outperforms the state-of-art generative models in the related areas.
    Original languageEnglish
    Title of host publicationProceedings of 2019 25th International Conference on Automation and Computing (ICAC)
    PublisherInstitute of Electrical Engineers
    Number of pages6
    ISBN (Electronic)978-1-8613-7665-7
    ISBN (Print)978-1-7281-2518-3
    DOIs
    Publication statusPublished - 11 Nov 2019
    Event25th IEEE International Conference on Automation and Computing - Lancaster, United Kingdom
    Duration: 5 Sept 20197 Sept 2019

    Conference

    Conference25th IEEE International Conference on Automation and Computing
    Abbreviated titleICAC'19
    Country/TerritoryUnited Kingdom
    CityLancaster
    Period5/09/197/09/19

    Fingerprint

    Dive into the research topics of 'Dual stage augmented colorful texture synthesis from hand sketch'. Together they form a unique fingerprint.

    Cite this