LayerD: Decomposing Raster Graphic Designs into Layers
This addresses a practical issue for graphic designers by allowing layer-based editing of composited raster images, though it is incremental as it builds on existing decomposition methods.
The paper tackles the problem of decomposing raster graphic designs into editable layers, enabling re-editable creative workflows, and shows that LayerD achieves high-quality decomposition and outperforms baselines.
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.