PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6018-6026
Abstract
Content-aware visual-textual presentation layout aims at arranging spatial space on the given canvas for pre-defined elements, including text, logo, and underlay, which is a key to automatic template-free creative graphic design. In practical applications, e.g., poster designs, the canvas is originally non-empty, and both inter-element relationships as well as inter-layer relationships should be concerned when generating a proper layout. A few recent works deal with them simultaneously, but they still suffer from poor graphic performance, such as a lack of layout variety or spatial non-alignment. Since content-aware visual-textual presentation layout is a novel task, we first construct a new dataset named PKU PosterLayout, which consists of 9,974 poster- layout pairs and 905 images, i.e., non-empty canvases. It is more challenging and useful for greater layout variety, domain diversity, and content diversity. Then, we propose design sequence formation (DSF) that reorganizes elements in layouts to imitate the design processes of human designers, and a novel CNN-LSTM-based conditional generative adversarial network (GAN) is presented to generate proper layouts. Specifically, the discriminator is design-sequence- aware and will supervise the “design” process of the generator. Experimental results verify the usefulness of the new benchmark and the effectiveness of the proposed approach, which achieves the best performance by generating suitable layouts for diverse canvases. The dataset and the source code are available at https://github.com/PKU-ICST-MIPL/PosterLayout-CVPR2023.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (61925201,62132001,62272013,U22B2048)
This publication has 19 references indexed in Scilit:
- Smarttext: Learning To Generate Harmonious Textual Layout Over Natural Image2020
- Attribute-Conditioned Layout GAN for Automatic Graphic DesignIEEE Transactions on Visualization and Computer Graphics, 2020
- Progressive Feature Polishing Network for Salient Object DetectionProceedings of the AAAI Conference on Artificial Intelligence, 2020
- A CNN-LSTM Approach to Human Activity Recognition2020
- LayoutGAN: Synthesizing Graphic Layouts With Vector-Wireframe Adversarial NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Content-aware generative modeling of graphic design layoutsACM Transactions on Graphics, 2019
- Automatic Generation of Visual-Textual Presentation LayoutACM Transactions on Multimedia Computing, Communications, and Applications, 2016
- Fast R-CNN2015
- DesignScape2015
- Learning Layouts for Single-PageGraphic DesignsIEEE Transactions on Visualization and Computer Graphics, 2014