Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Suzuki, Tomoyuki, Liu, Kang-Jun, Inoue, Naoto, Yamaguchi, Kota
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7084165466
Cites:
Cited by:
Related to: