合成分层设计数据是否有助于分层设计分解？
Does Synthetic Layered Design Data Benefit Layered Design Decomposition?
AI总结：
本文研究合成分层数据对图形设计分解的影响，发现纯合成数据能有效替代传统方法，且训练数据规模增加时性能提升，但5万样本后趋于饱和。
摘要：
近期图像生成技术的进步使高质量图像生成变得容易，但其输出本质上是扁平化的，将前景、背景和文本混合在固定画布中，导致生成后编辑困难。现有方法或依赖稀缺的专有分层资产，或从有限的结构先验构建部分合成数据，但两者在可扩展性上面临根本挑战。本文探讨纯合成分层数据是否能提升图形设计分解效果。我们假设在图形设计中，有效的分解不需要像自然图像组成那样精确建模层间依赖关系，因为设计元素通常是故意作为模块化和语义分离的组件排列的。具体而言，我们基于CLD基准线进行了数据导向的研究，构建了自有的合成数据集SynLayers，利用视觉语言模型生成文本监督，并用VLM预测的边界框自动化推理输入。我们的研究揭示了三个关键发现：(1) 即使仅使用纯合成数据训练，也能超越非可扩展的替代方案，如广泛使用的PrismLayersPro数据集，证明其作为可扩展和有效替代品的可行性；(2) 性能随着训练数据规模的增加而持续提升，但5万样本后收益趋于饱和；(3) 合成数据能够平衡层计数分布，避免现实世界数据集中常见的层计数不平衡问题。我们希望这项数据导向的研究能鼓励更广泛地采用合成数据作为实际分层设计编辑系统的基础。
英文摘要：
Recent advances in image generation have made it easy to produce high-quality images. However, these outputs are inherently flattened, entangling foreground elements, background, and text within a fixed canvas. As a result, flexible post-generation editing remains challenging, revealing a clear last-mile gap toward practical usability. Existing approaches either rely on scarce proprietary layered assets or construct partially synthetic data from limited structural priors. However, both strategies face fundamental challenges in scalability. In this work, we investigate whether pure synthetic layered data can improve graphic design decomposition. We make the assumption that, in graphic design, effective decomposition does not require modeling inter-layer dependencies as precisely as in natural-image composition, since design elements are often intentionally arranged as modular and semantically separable components. Concretely, we conduct a data-centric study based on CLD baseline, which is a state-of-the-art layer decomposition framework. Based on the baseline, we construct our own synthetic dataset, SynLayers, generate textual supervision using vision language models, and automate inference inputs with VLM-predicted bounding boxes. Our study reveals three key findings: (1) even training with purely synthetic data can outperform non-scalable alternatives such as the widely used PrismLayersPro dataset, demonstrating its viability as a scalable and effective substitute; (2) performance consistently improves with increased training data scale, while gains begin to saturate at around 50K samples; and (3) synthetic data enables balanced control over layer-count distributions, avoiding the layer-count imbalance commonly observed in real-world datasets. We hope this data-centric study encourages broader adoption of synthetic data as a practical foundation for layered design editing systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
