TY - GEN
T1 - Iconify
T2 - 3rd Joint International Workshop on Multimedia Artworks Analysis and International Workshop on Attractiveness Computing in Multimedia, MMArt-ACM 2020
AU - Karamatsu, Takuro
AU - Benitez-Garcia, Gibran
AU - Yanai, Keiji
AU - Uchida, Seiichi
N1 - Funding Information:
This work was supported by JSPS KAKENHI Grant Number JP17H06100.
Publisher Copyright:
© 2020 Copyright held by the owner/author(s).
PY - 2020/6/8
Y1 - 2020/6/8
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85086788413&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85086788413&partnerID=8YFLogxK
U2 - 10.1145/3379173.3393708
DO - 10.1145/3379173.3393708
M3 - Conference contribution
AN - SCOPUS:85086788413
T3 - MMArt-ACM 2020 - Proceedings of the 2020 Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia
SP - 7
EP - 12
BT - MMArt-ACM 2020 - Proceedings of the 2020 Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia
PB - Association for Computing Machinery
Y2 - 8 June 2020
ER -