Learning to Generate Posters of Scientific Papers

TL;DR

This paper introduces a data-driven framework for automatically generating scientific posters from papers, learning layout and design elements to produce readable, informative, and aesthetic posters.

Contribution

It is the first to model and generate scientific posters from papers using a graphical model-based approach and a newly collected dataset.

Findings

The approach effectively learns poster layouts and attributes.

Generated posters are comparable to human-designed posters.

The dataset supports future research in automated poster generation.

Abstract

Researchers often summarize their work in the form of posters. Posters provide a coherent and efficient way to convey core ideas from scientific papers. Generating a good scientific poster, however, is a complex and time consuming cognitive task, since such posters need to be readable, informative, and visually aesthetic. In this paper, for the first time, we study the challenging problem of learning to generate posters from scientific papers. To this end, a data-driven framework, that utilizes graphical models, is proposed. Specifically, given content to display, the key elements of a good poster, including panel layout and attributes of each panel, are learned and inferred from data. Then, given inferred layout and attributes, composition of graphical elements within each panel is synthesized. To learn and validate our model, we collect and make public a Poster-Paper dataset, which consists of scientific papers and corresponding posters with exhaustively labelled panels and attributes. Qualitative and quantitative results indicate the effectiveness of our approach.