Iconify:将照片转换成图标

Takuro Karamatsu, Gibran Benitez-Garcia, Keiji Yanai, S. Uchida
{"title":"Iconify:将照片转换成图标","authors":"Takuro Karamatsu, Gibran Benitez-Garcia, Keiji Yanai, S. Uchida","doi":"10.1145/3379173.3393708","DOIUrl":null,"url":null,"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.","PeriodicalId":416027,"journal":{"name":"Proceedings of the 2020 Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"Iconify: Converting Photographs into Icons\",\"authors\":\"Takuro Karamatsu, Gibran Benitez-Garcia, Keiji Yanai, S. Uchida\",\"doi\":\"10.1145/3379173.3393708\",\"DOIUrl\":null,\"url\":null,\"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.\",\"PeriodicalId\":416027,\"journal\":{\"name\":\"Proceedings of the 2020 Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia\",\"volume\":\"33 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-04-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2020 Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3379173.3393708\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2020 Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3379173.3393708","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8

摘要

在本文中,我们解决了照片和图标图像之间具有挑战性的域转换任务。虽然图标通常来源于真实的物体图像(即照片),但专业平面设计师在生成图标图像时采用了严格的抽象和简化。此外,这两个域之间没有一对一的对应关系,因此我们不能用它作为学习直接转换函数的基本真理。由于生成对抗网络(GAN)可以在没有任何对应的情况下处理域转换问题,我们测试了CycleGAN和UNIT从照片图像中分割的对象生成图标。我们在多个图像数据集上的实验证明,CycleGAN学习了足够的抽象和简化能力,可以生成类似图标的图像。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Iconify: Converting Photographs into Icons
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.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Automatic YouTube-Thumbnail Generation and Its Evaluation Proceedings of the 2020 Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia Style Image Retrieval for Improving Material Translation Using Neural Style Transfer Session details: Attractiveness Computing in Multimedia BatikGAN: A Generative Adversarial Network for Batik Creation
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1