Skip to content

Dual stage augmented colorful texture synthesis from hand sketch

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

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
Publication statusPublished - 11 Nov 2019
Event25th IEEE International Conference on Automation and Computing - Lancaster, United Kingdom
Duration: 5 Sep 20197 Sep 2019


Conference25th IEEE International Conference on Automation and Computing
Abbreviated titleICAC'19
CountryUnited Kingdom


  • Dual_Stage_Augmented_Colorful_Texture_Synthesis_from_Hand_Sketch_pp

    Rights statement: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

    Accepted author manuscript (Post-print), 0.98 MB, PDF document

Related information

Relations Get citation (various referencing formats)

ID: 18393457