将位图设计图自动拆解为可编辑的文字、背景和贴纸层
CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers
- 结合视觉语言模型与多分支扩散模型，实现分层解析
- 在两个数据集上整体性能提升23.7%，优于现有方法
- 适合需要高效编辑设计稿的UI/UX设计师使用
图形设计图像由多个可编辑层（如文字、背景、装饰元素）构成，而多数生成模型输出为无显式分层结构的位图，限制了后续编辑。现有解析方法通常依赖布局预测、抠图和修复等多阶段流水线，存在误差累积和可控性差的问题。本文提出一种混合生成框架，将位图设计图分解为可编辑的文字、背景和贴纸层。文字区域通过视觉语言模型解析为文本渲染协议，支持高保真重建与灵活重编辑；背景与贴纸层则采用支持RGBA的多分支扩散架构生成。我们进一步引入ParserReward，并结合组相对策略优化（Group Relative Policy Optimization），使生成质量更符合人类设计偏好。在Parser-40K与Crello两个挑战性数据集上的大量实验表明，本方法在所有指标上平均提升23.7%，显著优于现有方法。
原文摘要 · Abstract (English)
Graphic design images consist of multiple editable layers, such as text, background, and decorative elements, while most generative models produce rasterized outputs without explicit layer structures, limiting downstream editing. Existing graphic design parsing methods typically rely on multi-stage pipelines combining layout prediction, matting, and inpainting, which suffer from error accumulation and limited controllability. We propose a hybrid generative framework for raster-to-layer graphic design parsing that decomposes a design image into editable text, background, and sticker layers. Text regions are parsed using a vision-language model into a text rendering protocol, enabling faithful reconstruction and flexible re-editing, while background and sticker layers are generated using a multi-branch diffusion architecture with RGBA support. We further introduce ParserReward and integrate it with Group Relative Policy Optimization to align generation quality with human design preferences. Extensive experiments on two challenging datasets, \emph{i.e.,} the Parser-40K and Crello datasets, demonstrate superior performance over existing methods, \emph{eg.,} achieving an overall average improvement of 23.7\% across all metrics.
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。