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

HsiaoYuan Hsu, Yuxin Peng
Wangxuan Institute of Computer Technology, Peking University
IJCAI 2025 (AI, Arts and Creativity)
Paper (Coming soon) Code (Coming soon) arXiv (Coming soon)
Illustration of the content-aware layout generation task and the new efforts in this paper.

Content-aware layout generation task. (a) Heatmap-based paradigm. (b) Our new efforts: data summarization for efficient image perception and data augmentation for enhanced model generalization, aiming for real-time, robust performance.

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 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 patches and vertices across two image-layout pairs to synthesize over 100% new samples in each epoch while preserving their plausibility. To facilitate the vertex-level operations, we also introduced a vertex-based layout representation. 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%†.

†: Compared to the current state-of-the-art method, RALF [Horita et al., CVPR 2024 Oral].

The Proposed Approach: Scan-and-Print

An overview of Scan-and-Print.
An overview of Scan-and-Print.

(a) represents layout L based on the precise geometric properties, i.e., vertices, and grouping relationship, i.e., underlays, to facilitate the following fine-grained procedures; (b) efficiently 'scans' the input image I to perceive only the few patches suitable for arranging element vertices; (c) 'prints' the augmented samples (Ĩ, L̃) as extra training data by mixing patches and vertices across different pairs within the mini-batch to enhance the generalization ability of the autoregressive model.

BibTeX


@inproceedings{Hsu-IJCAI2025-ScanandPrint,
  title={Scan-and-Print: Patch-level Data Summarization and Augmentation for Content-aware Layout Generation in Poster Design},
  author={Hsu, HsiaoYuan and Peng, Yuxin},
  booktitle={Proceedings of the International Joint Conference on Artificial Intelligence},
  year={2025}
}