-
- Kotaro Kikuchi
- Waseda University, Shinjuku-ku, Japan
-
- Edgar Simo-Serra
- Waseda University, Shinjuku-ku, Japan
-
- Mayu Otani
- CyberAgent, Shibuya-ku, Japan
-
- Kota Yamaguchi
- CyberAgent, Shibuya-ku, Japan
説明
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 .
Accepted by ACM Multimedia 2021
収録刊行物
-
- Proceedings of the 29th ACM International Conference on Multimedia
-
Proceedings of the 29th ACM International Conference on Multimedia 88-96, 2021-10-17
ACM