ReDesign：通过智能体分解从图像中恢复可编辑的设计结构

摘要

从栅格图像恢复可编辑设计文件是现代设计工作流中常见且成本高昂的瓶颈，然而这一过程至今仍具挑战性，因为可编辑性依赖于恢复多模态属性，例如排版、矢量几何、颜色、分组与图层顺序。我们提出了ReDesign——一种智能代理框架，通过跨模态选择并组合专用工具，逐步构建可编辑的层级结构。为使这一长决策过程在工具输出不完美的情况下依然可靠，我们在每次层级扩展中引入了优雅验证机制：通过局部接受、剪枝或重试反馈，防止误差累积，避免大规模重运行。为在大规模场景下评估可编辑性，我们引入了Figma编辑重放基准，包含909个原始Figma文件及14,796条受控编辑指令，用于在重建输出上重放编辑操作。在该基准及标准重建指标上的实验表明，ReDesign在保持高视觉保真度的同时，在布局、颜色和文本编辑方面实现了最高的可编辑性，显著优于基于图层分解的基线方法及串行工具使用流程。

English

Recovering an editable design file from a raster image is a common and costly bottleneck in modern design workflows, yet remains challenging since editability depends on recovering multi-modal attributes, such as typography, vector geometry, colors, grouping, and layer ordering. We present ReDesign, an agentic framework that grows an editable layer hierarchy by selecting and composing specialized tools across modalities. To keep this long decision process reliable despite imperfect tool outputs, we introduce graceful verification at each expansion, which provides local accept, prune, or retry feedback that prevents error accumulation and avoids large scale reruns. To evaluate editability at scale, we introduce the Figma Edit Replay Benchmark, consisting of 909 raw Figma files and 14,796 controlled edit instructions that replay edits on reconstructed outputs. Across this benchmark and standard reconstruction metrics, ReDesign achieves strong visual fidelity while delivering the highest editability across layout, color, and text edits, outperforming layered decomposition baselines and serial tool use pipelines.