将合成后的位图图像拆解为可编辑的图层，恢复设计可修改性。
LayerD: Decomposing Raster Graphic Designs into Layers
- 通过迭代提取无遮挡前景图层，实现位图到图层的分解。
- 在真实设计数据集上达到高质量分解，优于现有方法。
- 适合需要逆向工程设计稿或结合生成模型编辑的创作者。
设计师通常以图层形式创作和编辑图形设计，但一旦合成位图后，图层编辑便不可行。本文提出 LayerD，一种将位图图形设计分解为可编辑图层的方法，以恢复可重编辑的设计工作流。LayerD 通过迭代提取未被遮挡的前景图层来解决分解任务，并提出一种简单有效的精炼方法，利用图形设计中图层常具均匀外观的假设。由于分解问题本身病态且真实图层结构可能不可靠，我们开发了一个质量度量来应对挑战。实验表明，LayerD 能成功实现高质量分解，性能超越基线方法。此外，我们还展示了 LayerD 与先进图像生成器及基于图层的编辑工具的集成应用。
原文摘要 · Abstract (English)
Designers craft and edit graphic designs in a layer representation, but layer-based editing becomes impossible once composited into a raster image. In this work, we propose LayerD, a method to decompose raster graphic designs into layers for re-editable creative workflow. LayerD addresses the decomposition task by iteratively extracting unoccluded foreground layers. We propose a simple yet effective refinement approach taking advantage of the assumption that layers often exhibit uniform appearance in graphic designs. As decomposition is ill-posed and the ground-truth layer structure may not be reliable, we develop a quality metric that addresses the difficulty. In experiments, we show that LayerD successfully achieves high-quality decomposition and outperforms baselines. We also demonstrate the use of LayerD with state-of-the-art image generators and layer-based editing.
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。