Doodle master: A doodle beautification system based on auto-encoding generative adversarial networks

Wen Cheng Chen, Chien Wen Chen, Min Chun Hu

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

2 Citations (Scopus)

Abstract

For those people without artistic talent, they can only draw rough or even awful doodles to express their ideas. We propose a doodle beautification system named Doodle Master, which can transfer a rough doodle to a plausible image and also keep the semantic concepts of the drawings. The Doodle Master applies the VAE/GAN model to decode and generate the beautified result from a constrained latent space. To achieve better performance for sketch data which is more like discrete distribution, a shared-weight method is proposed to improve the learnt features of the discriminator with the aid of the encoder. Furthermore, we design an interface for the user to draw with basic drawing tools and adjust the number of reconstruction times. The experiments show that the proposed Doodle Master system can successfully beautify the rough doodle or sketch in real-time.

Original languageEnglish
Title of host publicationMMArt and ACM 2018 - Proceedings of the 2018 International Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia, Co-located with ICMR 2018
PublisherAssociation for Computing Machinery, Inc
Pages2-7
Number of pages6
ISBN (Print)9781450357982
DOIs
Publication statusPublished - 2018 Jun 6
Event2018 International Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia, MMArt and ACM 2018 - Yokohama, Japan
Duration: 2018 Jun 11 → …

Publication series

NameMMArt and ACM 2018 - Proceedings of the 2018 International Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia, Co-located with ICMR 2018

Other

Other2018 International Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia, MMArt and ACM 2018
CountryJapan
CityYokohama
Period18-06-11 → …

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Doodle master: A doodle beautification system based on auto-encoding generative adversarial networks'. Together they form a unique fingerprint.

  • Cite this

    Chen, W. C., Chen, C. W., & Hu, M. C. (2018). Doodle master: A doodle beautification system based on auto-encoding generative adversarial networks. In MMArt and ACM 2018 - Proceedings of the 2018 International Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia, Co-located with ICMR 2018 (pp. 2-7). (MMArt and ACM 2018 - Proceedings of the 2018 International Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia, Co-located with ICMR 2018). Association for Computing Machinery, Inc. https://doi.org/10.1145/3209693.3209695