Constrained Graphic Layout Generation via Latent Optimization

Kotaro Kikuchi, Edgar Simo-Serra, Mayu Otani, Kota Yamaguchi

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

It is common in graphic design humans visually arrange various elements according to their design intent and semantics. For example, a title text almost always appears on top of other elements in a document. In this work, we generate graphic layouts that can flexibly incorporate such design semantics, either specified implicitly or explicitly by a user. We optimize using the latent space of an off-the-shelf layout generation model, allowing our approach to be complementary to and used with existing layout generation models. Our approach builds on a generative layout model based on a Transformer architecture, and formulates the layout generation as a constrained optimization problem where design constraints are used for element alignment, overlap avoidance, or any other user-specified relationship. We show in the experiments that our approach is capable of generating realistic layouts in both constrained and unconstrained generation tasks with a single model. The code is available at https://github.com/ktrk115/const_layout.

本文言語English
ホスト出版物のタイトルMM 2021 - Proceedings of the 29th ACM International Conference on Multimedia
出版社Association for Computing Machinery, Inc
ページ88-96
ページ数9
ISBN(電子版)9781450386517
DOI
出版ステータスPublished - 2021 10月 17
イベント29th ACM International Conference on Multimedia, MM 2021 - Virtual, Online, China
継続期間: 2021 10月 202021 10月 24

出版物シリーズ

名前MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia

Conference

Conference29th ACM International Conference on Multimedia, MM 2021
国/地域China
CityVirtual, Online
Period21/10/2021/10/24

ASJC Scopus subject areas

  • 人間とコンピュータの相互作用
  • ソフトウェア
  • コンピュータ グラフィックスおよびコンピュータ支援設計

フィンガープリント

「Constrained Graphic Layout Generation via Latent Optimization」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル