LayerD: Decomposing Raster Graphic Designs into Layers

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Suzuki, Tomoyuki, Liu, Kang-Jun, Inoue, Naoto, Yamaguchi, Kota
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916977150263296
author Suzuki, Tomoyuki
Liu, Kang-Jun
Inoue, Naoto
Yamaguchi, Kota
author_facet Suzuki, Tomoyuki
Liu, Kang-Jun
Inoue, Naoto
Yamaguchi, Kota
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25134
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LayerD: Decomposing Raster Graphic Designs into Layers
Suzuki, Tomoyuki
Liu, Kang-Jun
Inoue, Naoto
Yamaguchi, Kota
Graphics
Computer Vision and Pattern Recognition
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.
title LayerD: Decomposing Raster Graphic Designs into Layers
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.25134