从图片恢复可编辑设计文件，用智能工具链逐步构建层级结构。
ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition
- 用多模态工具链分步构建可编辑图层结构，支持字体、颜色、布局等属性还原。
- 在每一步加入容错验证，避免错误累积，提升整体重建可靠性。
- 首次提出可复现编辑的评测基准，实测显示其编辑保真度领先现有方法。
从位图图像中恢复可编辑的设计文件是现代设计流程中的常见且高成本瓶颈，但因需还原字体、矢量几何、颜色、分组和图层顺序等多模态属性而极具挑战。本文提出 ReDesign，一种通过选择并组合跨模态专用工具来逐步构建可编辑图层层级的智能体框架。为确保长序列决策过程的可靠性，引入逐级优雅验证机制，提供接受、剔除或重试反馈，防止误差累积并避免大规模重算。为实现可扩展的编辑性评估，我们构建了 Figma Edit Replay Benchmark，包含 909 个原始 Figma 文件和 14,796 条受控编辑指令，用于在重构结果上回放编辑操作。在该基准及标准重建指标下，ReDesign 在保持优异视觉保真度的同时，于布局、颜色和文本编辑任务中均展现出最高编辑性，优于分层分解基线与串行工具流水线。
原文摘要 · Abstract (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.
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。