Scan-and-Print: Patch-level Data Summarization and Augmentation for Content-aware Layout Generation in Poster Design

TL;DR

This paper introduces Scan-and-Print, a patch-level data summarization and augmentation method that improves content-aware poster layout generation by enhancing efficiency and generalization, achieving state-of-the-art results.

Contribution

The paper proposes a novel patch-level data augmentation technique and a vertex-based layout representation for efficient, high-quality poster layout generation.

Findings

Reduces computational bottleneck by 95.2%.

Generates over 100% new plausible samples per epoch.

Achieves state-of-the-art layout quality.

Abstract

In AI-empowered poster design, content-aware layout generation is crucial for the on-image arrangement of visual-textual elements, e.g., logo, text, and underlay. To perceive the background images, existing work demanded a high parameter count that far exceeds the size of available training data, which has impeded the model's real-time performance and generalization ability. To address these challenges, we proposed a patch-level data summarization and augmentation approach, vividly named Scan-and-Print. Specifically, the scan procedure selects only the patches suitable for placing element vertices to perform fine-grained perception efficiently. Then, the print procedure mixes up the patches and vertices across two image-layout pairs to synthesize over 100% new samples in each epoch while preserving their plausibility. Besides, to facilitate the vertex-level operations, a vertex-based layout representation is introduced. Extensive experimental results on widely used benchmarks demonstrated that Scan-and-Print can generate visually appealing layouts with state-of-the-art quality while dramatically reducing computational bottleneck by 95.2%.