发表机构
KAIST AI; Helmholtz Munich; Korea University（韩国科学技术院人工智能研究所; 慕尼黑亥姆霍兹中心; 韩国大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究旨在从图像恢复可编辑设计文件，提出ReDesign智能框架，通过跨模态选工具生成层层次结构，引入优雅验证与评估基准，在视觉保真度和编辑性上表现出色，超越基线和管道。
AI 中文摘要
从光栅图像恢复可编辑设计文件是现代设计工作流程中常见且成本高昂的瓶颈，因其依赖多模态属性恢复，极具挑战性。本文提出ReDesign，一个通过跨模态选择和组合专用工具来生成可编辑层层次结构的智能框架。为在工具输出不完善时保持决策可靠，引入了优雅验证，提供局部反馈。还引入Figma编辑重放基准进行评估。ReDesign在视觉保真度和编辑性上表现出色，优于分层分解基线和串行工具使用管道。
英文摘要
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.
CommentsAccepted to ECCV 2026
