通过分块扫描与打印，高效生成海报布局，提速95%以上。
Scan-and-Print: Patch-level Data Summarization and Augmentation for Content-aware Layout Generation in Poster Design
- 分块选择合适区域进行精细感知，提升效率
- 每轮生成超100%新样本，保持布局合理性
- 适合需要快速生成高质量海报的设计师
在人工智能赋能的海报设计中，内容感知布局生成对视觉文本元素（如标志、文字、底图）的图像内排布至关重要。现有方法需大量参数，远超训练数据规模，制约了模型实时性能与泛化能力。为此，本文提出分块数据摘要与增强方法——Scan-and-Print。首先，扫描过程仅选取适合放置元素顶点的图像块，实现高效细粒度感知；随后，打印过程在两组图像-布局对之间混合拼接块与顶点，每轮生成超过100%的新样本，同时保证布局合理性。此外，引入基于顶点的布局表示以支持顶点级操作。在多个主流基准上的实验表明，Scan-and-Print 能生成视觉吸引力强的布局，达到当前最优水平，且计算瓶颈降低95.2%。
原文摘要 · Abstract (English)
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%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。