mlsanityData to 14 Oct 2026

LayerD: Decomposing Raster Graphic Designs into Layers

arXiv 2509.25134 ↗First posted 29 Sep 2025cs.GR cs.CVcited by 21

Not on the map. Why?

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.

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

42 of 64 references.

References · 42

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2023Segment Anythingcited by 8,234
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  6. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  7. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  8. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  9. 2024YOLOv11: An Overview of the Key Architectural Enhancementscited by 425
  10. 2019Character Region Awareness for Text Detectioncited by 278
  11. 2024PaliGemma 2: A Family of Versatile VLMs for Transfercited by 207
  12. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 159
30 more
  1. 2017Deep Image Mattingcited by 150
  2. 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 116
  3. 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
  4. 2020Self-Supervised Scene De-occlusioncited by 96
  5. 2021CanvasVAE: Learning to Generate Vector Graphic Documentscited by 95
  6. 2023DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignmentcited by 90
  7. 2019Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimationcited by 79
  8. 2022Towards Layer-wise Image Vectorizationcited by 79
  9. 2017Information-Flow Mattingcited by 59
  10. 2023ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformerscited by 56
  11. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  12. 2024MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generationcited by 38
  13. 2023Text2Layer: Layered Image Generation using Latent Diffusion Modelcited by 37
  14. 2024OpenCOLE: Towards Reproducible Automatic Graphic Design Generationcited by 37
  15. 2022CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphicscited by 34
  16. 2024Generative Image Layer Decomposition with Visual Effectscited by 34
  17. 2021Instance-wise Occlusion and Depth Orders in Natural Scenescited by 31
  18. 2024Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentationcited by 30
  19. 2021De-rendering Stylized Textscited by 24
  20. 2021Visiting the Invisible: Layer-by-Layer Completed Scene Decompositioncited by 23
  21. 2021ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesiscited by 23
  22. 2024Object-level Scene Deocclusioncited by 17
  23. 2020Fast Soft Color Segmentationcited by 13
  24. 2024From Elements to Design: A Layered Approach for Automatic Graphic Design Compositioncited by 13
  25. 2024LogoMotion: Visually-Grounded Code Synthesis for Creating and Editing Animationcited by 10
  26. 2025Rethinking Layered Graphic Design Generation with a Top-Down Approachcited by 10
  27. 2025AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Modelscited by 9
  28. 2020Fast Multi-Level Foreground Estimationcited by 5
  29. 2024Fast Sprite Decomposition from Animated Graphicscited by 2
  30. 2021Foreground color prediction through inverse compositingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 19.

21 papers.

Sort:

By area:

  1. 2025Qwen-Image-Layered: Towards Inherent Editability via Layer Decompositioncited by 34
  2. 2026CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layerscited by 9
  3. 2026DesignAsCode: Bridging Structural Editability and Visual Fidelity in Graphic Design Generationcited by 5
  4. 2026LaDe: Unified Multi-Layered Graphic Media Generation and Decompositioncited by 5
  5. 2026See-through: Single-image Layer Decomposition for Anime Characterscited by 3
  6. 2025VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridgingcited by 2
  7. 2026Workflow-Aware Structured Layer Decomposition for Illustration Productioncited by 1
  8. 2026RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decompositioncited by 1
  9. 2026LiWi: Layering in the Wildcited by 1
  10. 2026Does Synthetic Layered Design Data Benefit Layered Design Decomposition?cited by 1
  11. 2026Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learningcited by 1
  12. 2026Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detectioncited by 1
9 more
  1. 2026Cycle-Consistent Tuning for Layered Image Decompositioncited by 0
  2. 2026LimeCross: Context-Conditioned Layered Image Editing with Structural Consistencycited by 0
  3. 2026UniWorld-Design: From Pixel Generation to Layer-Native Designcited by 0
  4. 2026GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Paperscited by 0
  5. 2026Mise-en-Sc`ene: Implicit Layout Emergence in Diffusion Transformers for Human-AI Design Co-Creationcited by 0
  6. 2026Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Modelscited by 0
  7. 2026SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifactscited by 0
  8. 2026VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphicscited by 0
  9. 2026PixelART: Image-to-Layer Decomposition without Latents or Text-to-Image Pretrainingcited by 0