AI把图片拆成可编辑设计稿，像拆乐高
设计师拿到一张图片想改字体、调颜色、挪图层，通常得从头画一遍。这篇让AI像拆乐高一样，把图片拆成可编辑的图层结构：字体、矢量图形、颜色、分组、图层顺序全部分开。关键是一边拆一边检查——拆错就重来，不把错误堆到后面。在909个真实Figma文件上测试，改布局、改颜色、改文字都比现有方法靠谱。它不是你明天就能用的工具，但指向一个方向：AI不再只是生成一张图，而是生成你能动手改的源文件。
📄 原文摘要(英文)
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.