LayerD: Decomposing Raster Graphic Designs into Layers

2025-09-29

AI Summary

To address the irreversibility of layer editing in rasterized image generation, this paper proposes an invertible layer decomposition method. It iteratively extracts occlusion-free foreground layers and introduces a novel quality metric grounded in layer-wise visual consistency—commonly observed in professional graphic design—to alleviate the ill-posedness of decomposition. The method adopts a two-stage strategy: “progressive extraction” followed by “refinement optimization,” integrating domain-specific priors with state-of-the-art generative models (e.g., diffusion models) for layer reconstruction and validation. Experiments demonstrate substantial improvements over existing baselines across multiple benchmarks, yielding layers with high fidelity and precise editability. Furthermore, the method has been integrated into mainstream image generation and layer-editing toolchains, enabling robust, re-editable creative workflows.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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.

Problem

• Decomposing raster graphics into editable layers
• Enabling re-editable workflows from composite images
• Extracting uniform appearance layers iteratively

Innovation

• Iteratively extracts unoccluded foreground layers
• Refines layers assuming uniform appearance assumption
• Develops quality metric addressing decomposition ambiguity