LayerD：將柵格圖形設計分解為圖層

LayerD: Decomposing Raster Graphic Designs into Layers

September 29, 2025

作者: Tomoyuki Suzuki, Kang-Jun Liu, Naoto Inoue, Kota Yamaguchi

cs.AI

摘要

設計師在圖層表示中製作和編輯圖形設計，但一旦合成為點陣圖像，基於圖層的編輯就變得不可能。在本研究中，我們提出了LayerD，一種將點陣圖形設計分解為圖層的方法，以實現可重新編輯的創意工作流程。LayerD通過迭代提取未被遮擋的前景圖層來解決分解任務。我們提出了一種簡單而有效的精煉方法，利用圖形設計中圖層通常呈現均勻外觀的假設。由於分解問題本身是不適定的，且真實圖層結構可能不可靠，我們開發了一種質量指標來應對這一難題。在實驗中，我們展示了LayerD成功實現了高質量的分解，並超越了基線方法。我們還展示了LayerD與最先進的圖像生成器和基於圖層的編輯的結合應用。

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.