# LayerD: Decomposing Raster Graphic Designs into Layers

arXiv: https://arxiv.org/abs/2509.25134 · HTML: https://mlsanity.com/paper/2509.25134/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 64 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 30 of 42)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [PaliGemma 2: A Family of Versatile VLMs for Transfer](https://mlsanity.com/paper/2412.03555/) (2024)
- [DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation](https://mlsanity.com/paper/2007.11301/) (2020)
- [Deep Image Matting](https://mlsanity.com/paper/1703.03872/) (2017)
- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [Bilateral Reference for High-Resolution Dichotomous Image Segmentation](https://mlsanity.com/paper/2401.03407/) (2024)
- [Self-Supervised Scene De-occlusion](https://mlsanity.com/paper/2004.02788/) (2020)
- [CanvasVAE: Learning to Generate Vector Graphic Documents](https://mlsanity.com/paper/2108.01249/) (2021)
- [DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment](https://mlsanity.com/paper/2304.04514/) (2023)
- [Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation](https://mlsanity.com/paper/1909.09725/) (2019)
- [Towards Layer-wise Image Vectorization](https://mlsanity.com/paper/2206.04655/) (2022)
- [Information-Flow Matting](https://mlsanity.com/paper/1707.05055/) (2017)
- [ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers](https://mlsanity.com/paper/2305.15272/) (2023)
- [Unsupervised Layered Image Decomposition into Object Prototypes](https://mlsanity.com/paper/2104.14575/) (2021)
- [MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation](https://mlsanity.com/paper/2404.02790/) (2024)
- [Text2Layer: Layered Image Generation using Latent Diffusion Model](https://mlsanity.com/paper/2307.09781/) (2023)
- [OpenCOLE: Towards Reproducible Automatic Graphic Design Generation](https://mlsanity.com/paper/2406.08232/) (2024)
- [CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics](https://mlsanity.com/paper/2212.02122/) (2022)
- [Generative Image Layer Decomposition with Visual Effects](https://mlsanity.com/paper/2411.17864/) (2024)
- [Instance-wise Occlusion and Depth Orders in Natural Scenes](https://mlsanity.com/paper/2111.14562/) (2021)
- [Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation](https://mlsanity.com/paper/2401.17904/) (2024)

## Built on by (most cited first, 21 of 21)

- [Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition](https://mlsanity.com/paper/2512.15603/) (2025)
- [CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers](https://mlsanity.com/paper/2604.19632/) (2026)
- [DesignAsCode: Bridging Structural Editability and Visual Fidelity in Graphic Design Generation](https://mlsanity.com/paper/2602.17690/) (2026)
- [LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition](https://mlsanity.com/paper/2603.17965/) (2026)
- [See-through: Single-image Layer Decomposition for Anime Characters](https://mlsanity.com/paper/2602.03749/) (2026)
- [VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging](https://mlsanity.com/paper/2511.18121/) (2025)
- [Workflow-Aware Structured Layer Decomposition for Illustration Production](https://mlsanity.com/paper/2603.14925/) (2026)
- [RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition](https://mlsanity.com/paper/2605.11818/) (2026)
- [LiWi: Layering in the Wild](https://mlsanity.com/paper/2605.14552/) (2026)
- [Does Synthetic Layered Design Data Benefit Layered Design Decomposition?](https://mlsanity.com/paper/2605.15167/) (2026)
- [Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning](https://mlsanity.com/paper/2605.30257/) (2026)
- [Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection](https://mlsanity.com/paper/2609.07072/) (2026)
- [Cycle-Consistent Tuning for Layered Image Decomposition](https://mlsanity.com/paper/2602.20989/) (2026)
- [LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency](https://mlsanity.com/paper/2605.10319/) (2026)
- [UniWorld-Design: From Pixel Generation to Layer-Native Design](https://mlsanity.com/paper/2608.03971/) (2026)
- [GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Papers](https://mlsanity.com/paper/2608.05478/) (2026)
- [Mise-en-Sc`ene: Implicit Layout Emergence in Diffusion Transformers for Human-AI Design Co-Creation](https://mlsanity.com/paper/2608.19000/) (2026)
- [Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Models](https://mlsanity.com/paper/2608.26716/) (2026)
- [SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts](https://mlsanity.com/paper/2609.03109/) (2026)
- [VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphics](https://mlsanity.com/paper/2609.13294/) (2026)
- [PixelART: Image-to-Layer Decomposition without Latents or Text-to-Image Pretraining](https://mlsanity.com/paper/2609.22789/) (2026)

## Abstract (arXiv)

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.