SciPostGen: Bridging the Gap between Scientific Papers and Poster Layouts

TL;DR

This paper introduces SciPostGen, a large dataset linking scientific papers to poster layouts, and proposes a retrieval-augmented framework for generating poster layouts that reflect paper structure and constraints.

Contribution

The paper presents SciPostGen, a novel dataset for paper-to-poster layout understanding, and a retrieval-augmented method for generating layouts aligned with paper content.

Findings

Paper structures correlate with the number of poster layout elements.

The retrieval-augmented framework produces layouts consistent with paper structures.

Layouts generated satisfy constraints specified by poster creators.

Abstract

As the number of scientific papers continues to grow, there is a demand for approaches that can effectively convey research findings, with posters serving as a key medium for presenting paper contents. Poster layouts determine how effectively research is communicated and understood, highlighting their growing importance. In particular, a gap remains in understanding how papers correspond to the layouts that present them, which calls for datasets with paired annotations at scale. To bridge this gap, we introduce SciPostGen, a large-scale dataset for understanding and generating poster layouts from scientific papers. Our analyses based on SciPostGen show that paper structures are associated with the number of layout elements in posters. Based on this insight, we explore a framework, Retrieval-Augmented Poster Layout Generation, which retrieves layouts consistent with a given paper and uses them as guidance for layout generation. We conducted experiments under two conditions: with and without layout constraints typically specified by poster creators. The results show that the retriever estimates layouts aligned with paper structures, and our framework generates layouts that also satisfy given constraints. The dataset and code are publicly available at https://omron-sinicx.github.io/paper2layout/.