Iconify: converting photographs into icons

Takuro Karamatsu, Gibran Benitez-Garcia, Seiichi Uchida

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we tackle a challenging domain conversion task between photo and icon images. Although icons often originate from real object images (i.e., photographs), severe abstractions and simplifications are applied to generate icon images by professional graphic designers. Moreover, there is no one-to-one correspondence between the two domains, for this reason we cannot use it as the ground-truth for learning a direct conversion function. Since generative adversarial networks (GAN) can undertake the problem of domain conversion without any correspondence, we test CycleGAN and UNIT to generate icons from objects segmented from photo images. Our experiments with several image datasets prove that CycleGAN learns sufficient abstraction and simplification ability to generate icon-like images.

Original languageEnglish
JournalUnknown Journal
Publication statusPublished - Apr 7 2020

All Science Journal Classification (ASJC) codes

  • General

Fingerprint Dive into the research topics of 'Iconify: converting photographs into icons'. Together they form a unique fingerprint.

Cite this