mlsanityData to 7 Oct 2026

De-rendering Stylized Texts

arXiv 2110.01890 ↗First posted 5 Oct 2021cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

Editing raster text is a promising but challenging task. We propose to apply text vectorization for the task of raster text editing in display media, such as posters, web pages, or advertisements. In our approach, instead of applying image transformation or generation in the raster domain, we learn a text vectorization model to parse all the rendering parameters including text, location, size, font, style, effects, and hidden background, then utilize those parameters for reconstruction and any editing task. Our text vectorization takes advantage of differentiable text rendering to accurately reproduce the input raster text in a resolution-free parametric format. We show in the experiments that our approach can successfully parse text, styling, and background information in the unified model, and produces artifact-free text editing compared to a raster baseline.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 29 of its 53 references that are in the map. First posted on arXiv 5 Oct 2021.

Builds on

29 of 53 references.

References · 29

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  2. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  3. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  4. 2019Character Region Awareness for Text Detectioncited by 273
  5. 2017EAST: An Efficient and Accurate Scene Text Detectorcited by 248
  6. 2019Real-time Scene Text Detection with Differentiable Binarizationcited by 212
  7. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 158
  8. 2018FOTS: Fast Oriented Text Spotting with a Unified Networkcited by 109
  9. 2020Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizationscited by 102
  10. 2017Multi-Content GAN for Few-Shot Font Style Transfercited by 100
  11. 2019Editing Text in the Wildcited by 81
  12. 2017Automatic Understanding of Image and Video Advertisementscited by 67
17 more
  1. 2019Convolutional Character Networkscited by 61
  2. 2020SwapText: Image Based Texts Transfer in Scenescited by 49
  3. 2019STEFANN: Scene Text Editor using Font Adaptive Neural Networkcited by 46
  4. 2019Controllable Artistic Text Style Transfer via Shape-Matching GANcited by 45
  5. 2017BAM! The Behance Artistic Media Dataset for Recognition Beyond Photographycited by 43
  6. 2020B'ezierSketch: A generative model for scalable vector sketchescited by 43
  7. 2019MTRNet: A Generic Scene Text Erasercited by 29
  8. 2018EnsNet: Ensconce Text in the Wildcited by 27
  9. 2017Scene Text Erasercited by 26
  10. 2015DeepFont: Identify Your Font from An Imagecited by 24
  11. 2016Awesome Typography: Statistics-Based Text Effects Transfercited by 24
  12. 2020Deep Vectorization of Technical Drawingscited by 23
  13. 2018Retrieval-Enhanced Adversarial Training for Neural Response Generationcited by 22
  14. 2019Large-scale Tag-based Font Retrieval with Generative Feature Learningcited by 22
  15. 2018Vectorization of Line Drawings via PolyVector Fieldscited by 16
  16. 2018Context-Aware Text-Based Binary Image Stylization and Synthesiscited by 11
  17. 2020Character-independent font identificationcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 10; 2024: 7; 2025: 3.

24 papers.

Sort:

By area:

  1. 2023TextDiffuser: Diffusion Models as Text Painterscited by 223
  2. 2022Towards Layer-wise Image Vectorizationcited by 77
  3. 2023Improving Diffusion Models for Scene Text Editing with Dual Encoderscited by 44
  4. 2023DiffUTE: Universal Text Editing Diffusion Modelcited by 44
  5. 2024Revisiting Tampered Scene Text Detection in the Era of Generative AIcited by 21
  6. 2025LayerD: Decomposing Raster Graphic Designs into Layerscited by 20
  7. 2022Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Contextcited by 18
  8. 2024DreamText: High Fidelity Scene Text Synthesiscited by 17
  9. 2022Unsupervised Structure-Texture Separation Network for Oracle Character Recognitioncited by 15
  10. 2023Towards Diverse and Consistent Typography Generationcited by 11
  11. 2024Kinetic Typography Diffusion Modelcited by 9
  12. 2024How Control Information Influences Multilingual Text Image Generation and Editing?cited by 9
12 more
  1. 2024Intelligent Artistic Typography: A Comprehensive Review of Artistic Text Design and Generationcited by 9
  2. 2025Rethinking Layered Graphic Design Generation with a Top-Down Approachcited by 9
  3. 2023FASTER: A Font-Agnostic Scene Text Editing and Rendering Frameworkcited by 6
  4. 2023On Manipulating Scene Text in the Wild with Diffusion Modelscited by 6
  5. 2022APRNet: Attention-based Pixel-wise Rendering Network for Photo-Realistic Text Image Generationcited by 3
  6. 2024DeepEraser: Deep Iterative Context Mining for Generic Text Erasercited by 3
  7. 2023Selective Scene Text Removalcited by 2
  8. 2024Fast Sprite Decomposition from Animated Graphicscited by 2
  9. 2023Image Generation and Learning Strategy for Deep Document Forgery Detectioncited by 1
  10. 2023Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Modelscited by 0
  11. 2023Optimize and Reduce: A Top-Down Approach for Image Vectorizationcited by 0
  12. 2025Inverse Scene Text Removalcited by 0