mlsanityData to 14 Oct 2026

FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework

arXiv 2308.02905 ↗First posted 5 Aug 2023cs.CV cs.MMcited by 6

Not on the map. Why?

Abstract (arXiv)

Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world applications, existing style-transfer-based approaches have shown sub-par editing performance due to (1) complex image backgrounds, (2) diverse font attributes, and (3) varying word lengths within the text. To address such limitations, in this paper, we propose a novel font-agnostic scene text editing and rendering framework, named FASTER, for simultaneously generating text in arbitrary styles and locations while preserving a natural and realistic appearance and structure. A combined fusion of target mask generation and style transfer units, with a cascaded self-attention mechanism has been proposed to focus on multi-level text region edits to handle varying word lengths. Extensive evaluation on a real-world database with further subjective human evaluation study indicates the superiority of FASTER in both scene text editing and rendering tasks, in terms of model performance and efficiency. Our code will be released upon acceptance.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 53 of its 73 references that are in the map. First posted on arXiv 5 Aug 2023.

Builds on

53 of 73 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  7. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  8. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  9. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  10. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  11. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  12. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
38 more
  1. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  2. 2018Self-Attention Generative Adversarial Networkscited by 809
  3. 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
  4. 2019Character Region Awareness for Text Detectioncited by 278
  5. 2023TextDiffuser: Diffusion Models as Text Painterscited by 229
  6. 2014Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognitioncited by 214
  7. 2019What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysiscited by 191
  8. 2019ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019cited by 139
  9. 2017Multi-Content GAN for Few-Shot Font Style Transfercited by 100
  10. 2021CanvasVAE: Learning to Generate Vector Graphic Documentscited by 95
  11. 2019Editing Text in the Wildcited by 82
  12. 2021On the Integration of Self-Attention and Convolutioncited by 74
  13. 2018Spatial Fusion GAN for Image Synthesiscited by 68
  14. 2017Separating Style and Content for Generalized Style Transfercited by 64
  15. 2020SwapText: Image Based Texts Transfer in Scenescited by 50
  16. 2021TextStyleBrush: Transfer of Text Aesthetics from a Single Examplecited by 49
  17. 2019STEFANN: Scene Text Editor using Font Adaptive Neural Networkcited by 47
  18. 2021Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Expertscited by 46
  19. 2019Controllable Artistic Text Style Transfer via Shape-Matching GANcited by 45
  20. 2023Improving Diffusion Models for Scene Text Editing with Dual Encoderscited by 45
  21. 2023DiffUTE: Universal Text Editing Diffusion Modelcited by 45
  22. 2018Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenescited by 44
  23. 2019GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognitioncited by 37
  24. 2022Exploring Stroke-Level Modifications for Scene Text Editingcited by 37
  25. 2022Content and Style Aware Generation of Text-line Images for Handwriting Recognitioncited by 35
  26. 2023Handwritten Text Generation from Visual Archetypescited by 32
  27. 2022OCR-VQGAN: Taming Text-within-Image Generationcited by 31
  28. 2023Towards Flexible Multi-modal Document Modelscited by 31
  29. 2016Awesome Typography: Statistics-Based Text Effects Transfercited by 24
  30. 2021De-rendering Stylized Textscited by 24
  31. 2021Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detectioncited by 23
  32. 2016Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layoutscited by 21
  33. 2018TET-GAN: Text Effects Transfer via Stylization and Destylizationcited by 19
  34. 2021Deep Learning-based Forgery Attack on Document Imagescited by 14
  35. 2021STRIVE: Scene Text Replacement In Videoscited by 13
  36. 2021Mobile Augmented Reality: User Interfaces, Frameworks, and Intelligencecited by 10
  37. 2021RewriteNet: Reliable Scene Text Editing with Implicit Decomposition of Text Contents and Stylescited by 10
  38. 2022Multi-scale Attention Guided Pose Transfercited by 10

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 0; 2026: 2.

6 papers.

  1. 2024Intelligent Artistic Typography: A Comprehensive Review of Artistic Text Design and Generationcited by 9
  2. 2024Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processingcited by 8
  3. 2023Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenescited by 2
  4. 2023Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performancecited by 1
  5. 2026Towards Training-Free Scene Text Editingcited by 1
  6. 2026DRG-Font: Dynamic Reference-Guided Few-shot Font Generation via Contrastive Style-Content Disentanglementcited by 0