Text2Poster: Laying out Stylized Texts on Retrieved Images
This addresses the time-consuming and skill-intensive task of poster generation for applications requiring automated design, though it appears incremental as it builds on existing methods like pretrained models and auto-encoders.
The paper tackles the problem of automatically generating visually-effective posters from text, proposing Text2Poster, a data-driven framework that retrieves images, lays out text iteratively, and stylizes text, with experiments showing it outperforms state-of-the-art methods and commercial software in quality.
Poster generation is a significant task for a wide range of applications, which is often time-consuming and requires lots of manual editing and artistic experience. In this paper, we propose a novel data-driven framework, called \textit{Text2Poster}, to automatically generate visually-effective posters from textual information. Imitating the process of manual poster editing, our framework leverages a large-scale pretrained visual-textual model to retrieve background images from given texts, lays out the texts on the images iteratively by cascaded auto-encoders, and finally, stylizes the texts by a matching-based method. We learn the modules of the framework by weakly- and self-supervised learning strategies, mitigating the demand for labeled data. Both objective and subjective experiments demonstrate that our Text2Poster outperforms state-of-the-art methods, including academic research and commercial software, on the quality of generated posters.