mlsanityData to 7 Oct 2026

CanvasVAE: Learning to Generate Vector Graphic Documents

arXiv 2108.01249 ↗First posted 3 Aug 2021cs.CVcited by 93

Not on the map. Why?

Abstract (arXiv)

Vector graphic documents present visual elements in a resolution free, compact format and are often seen in creative applications. In this work, we attempt to learn a generative model of vector graphic documents. We define vector graphic documents by a multi-modal set of attributes associated to a canvas and a sequence of visual elements such as shapes, images, or texts, and train variational auto-encoders to learn the representation of the documents. We collect a new dataset of design templates from an online service that features complete document structure including occluded elements. In experiments, we show that our model, named CanvasVAE, constitutes a strong baseline for generative modeling of vector graphic documents.

Key facts. Cited by 93 papers in the map (data through 7 Oct 2026). Builds on 21 of its 34 references that are in the map. First posted on arXiv 3 Aug 2021.

Builds on

21 of 34 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  5. 2019PubLayNet: largest dataset ever for document layout analysiscited by 349
  6. 2018Image Generation from Scene Graphscited by 324
  7. 2017A Neural Representation of Sketch Drawingscited by 311
  8. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 158
  9. 2019LayoutGAN: Generating Graphic Layouts with Wireframe Discriminatorscited by 130
  10. 2019LayoutVAE: Stochastic Scene Layout Generation From a Label Setcited by 119
  11. 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 114
  12. 2019A Learned Representation for Scalable Vector Graphicscited by 91
9 more
  1. 2021Variational Transformer Networks for Layout Generationcited by 88
  2. 2019Neural Design Network: Graphic Layout Generation with Constraintscited by 83
  3. 2018Synthesizing Programs for Images using Reinforced Adversarial Learningcited by 72
  4. 2020Attribute-conditioned Layout GAN for Automatic Graphic Designcited by 67
  5. 2019READ: Recursive Autoencoders for Document Layout Generationcited by 51
  6. 2020B'ezierSketch: A generative model for scalable vector sketchescited by 43
  7. 2021Screen2Vec: Semantic Embedding of GUI Screens and GUI Componentscited by 41
  8. 2018Vectorization of Line Drawings via PolyVector Fieldscited by 16
  9. 2017Feedback-prop: Convolutional Neural Network Inference under Partial Evidencecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 13; 2024: 25; 2025: 20; 2026: 29.

93 papers.

Sort:

By area:

  1. 2022VectorMapNet: End-to-end Vectorized HD Map Learningcited by 243
  2. 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generationcited by 141
  3. 2021BLT: Bidirectional Layout Transformer for Controllable Layout Generationcited by 69
  4. 2022A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibilitycited by 61
  5. 2023LayoutDM: Transformer-based Diffusion Model for Layout Generationcited by 57
  6. 2022LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restrictioncited by 43
  7. 2023Unifying Layout Generation with a Decoupled Diffusion Modelcited by 41
  8. 2023LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Modelscited by 40
  9. 2023COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Designcited by 39
  10. 2024PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLMcited by 39
  11. 2024Graphic Design with Large Multimodal Modelcited by 38
  12. 2025ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generationcited by 37
38 more
  1. 2024OpenCOLE: Towards Reproducible Automatic Graphic Design Generationcited by 36
  2. 2024PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generationcited by 34
  3. 2023Towards Flexible Multi-modal Document Modelscited by 30
  4. 2025Qwen-Image-Layered: Towards Inherent Editability via Layer Decompositioncited by 29
  5. 2023PLay: Parametrically Conditioned Layout Generation using Latent Diffusioncited by 24
  6. 2023Dolfin: Diffusion Layout Transformers without Autoencodercited by 23
  7. 2024LayoutFlow: Flow Matching for Layout Generationcited by 21
  8. 2024Alfie: Democratising RGBA Image Generation With No cited by 20
  9. 2025LayerD: Decomposing Raster Graphic Designs into Layerscited by 20
  10. 2024Desigen: A Pipeline for Controllable Design Template Generationcited by 19
  11. 2023LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Modelscited by 17
  12. 2025CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generationcited by 17
  13. 2022LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designercited by 15
  14. 2023A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptionscited by 15
  15. 2024Multimodal Markup Document Models for Graphic Design Completioncited by 15
  16. 2024SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posterscited by 14
  17. 2024VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correctioncited by 14
  18. 2025PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Modelscited by 14
  19. 2023Towards Diverse and Consistent Typography Generationcited by 11
  20. 2024From Elements to Design: A Layered Approach for Automatic Graphic Design Compositioncited by 11
  21. 2024LTSim: Layout Transportation-based Similarity Measure for Evaluating Layout Generationcited by 10
  22. 2024DOGR: Towards Versatile Visual Document Grounding and Referringcited by 10
  23. 2022Color Recommendation for Vector Graphic Documents based on Multi-Palette Representationcited by 9
  24. 2025Rethinking Layered Graphic Design Generation with a Top-Down Approachcited by 9
  25. 2025AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Modelscited by 8
  26. 2026CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layerscited by 8
  27. 2024DesignProbe: A Graphic Design Benchmark for Multimodal Large Language Modelscited by 7
  28. 2024Automatic Layout Planning for Visually-Rich Documents with Instruction-Following Modelscited by 7
  29. 2024Layout-Corrector: Alleviating Layout Sticking Phenomenon in Discrete Diffusion Modelcited by 7
  30. 2024TextLap: Customizing Language Models for Text-to-Layout Planningcited by 7
  31. 2023FASTER: A Font-Agnostic Scene Text Editing and Rendering Frameworkcited by 6
  32. 2025SEGA: A Stepwise Evolution Paradigm for Content-Aware Layout Generation with Design Priorcited by 6
  33. 2026Can Vision Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspectivecited by 6
  34. 2026LICA: Layered Image Composition Annotations for Graphic Design Researchcited by 6
  35. 2023Multimodal Color Recommendation in Vector Graphic Documentscited by 5
  36. 2024Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generationcited by 5
  37. 2024DocSynthv2: A Practical Autoregressive Modeling for Document Generationcited by 5
  38. 2024Design-o-meter: Towards Evaluating and Refining Graphic Designscited by 5

50 most cited of 93 All 93 (JSON)