# TextStyleBrush: Transfer of Text Aesthetics from a Single Example

arXiv: https://arxiv.org/abs/2106.08385 · HTML: https://mlsanity.com/paper/2106.08385/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 72 references that are in the map.
- First posted on arXiv 15 Jun 2021.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Few-Shot Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1905.01723/) (2019)
- [The Deepfake Detection Challenge (DFDC) Preview Dataset](https://mlsanity.com/paper/1910.08854/) (2019)
- [What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis](https://mlsanity.com/paper/1904.01906/) (2019)
- [TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text](https://mlsanity.com/paper/2105.05486/) (2021)
- [Scene Text Detection and Recognition: The Deep Learning Era](https://mlsanity.com/paper/1811.04256/) (2018)
- [Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting](https://mlsanity.com/paper/2007.09482/) (2020)
- [Multi-Content GAN for Few-Shot Font Style Transfer](https://mlsanity.com/paper/1712.00516/) (2017)
- [Editing Text in the Wild](https://mlsanity.com/paper/1908.03047/) (2019)
- [ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation](https://mlsanity.com/paper/2003.10557/) (2020)
- [Spatial Fusion GAN for Image Synthesis](https://mlsanity.com/paper/1812.05840/) (2018)
- [GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images](https://mlsanity.com/paper/2003.02567/) (2020)
- [Geometry Score: A Method For Comparing Generative Adversarial Networks](https://mlsanity.com/paper/1802.02664/) (2018)
- [SwapText: Image Based Texts Transfer in Scenes](https://mlsanity.com/paper/2003.08152/) (2020)
- [STEFANN: Scene Text Editor using Font Adaptive Neural Network](https://mlsanity.com/paper/1903.01192/) (2019)

## Built on by (most cited first, 30 of 49)

- [TextDiffuser: Diffusion Models as Text Painters](https://mlsanity.com/paper/2305.10855/) (2023)
- [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://mlsanity.com/paper/2211.08332/) (2022)
- [FineVision: Open Data Is All You Need](https://mlsanity.com/paper/2510.17269/) (2025)
- [Improving Diffusion Models for Scene Text Editing with Dual Encoders](https://mlsanity.com/paper/2304.05568/) (2023)
- [TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control](https://mlsanity.com/paper/2410.10133/) (2024)
- [Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model](https://mlsanity.com/paper/2312.12232/) (2023)
- [Handwritten Text Generation from Visual Archetypes](https://mlsanity.com/paper/2303.15269/) (2023)
- [LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding](https://mlsanity.com/paper/2605.27365/) (2026)
- [Visual Text Processing: A Comprehensive Review and Unified Evaluation](https://mlsanity.com/paper/2504.21682/) (2025)
- [Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context](https://mlsanity.com/paper/2207.10273/) (2022)
- [TextPainter: Multimodal Text Image Generation with Visual-harmony and Text-comprehension for Poster Design](https://mlsanity.com/paper/2308.04733/) (2023)
- [VATr++: Choose Your Words Wisely for Handwritten Text Generation](https://mlsanity.com/paper/2402.10798/) (2024)
- [Layout Agnostic Scene Text Image Synthesis with Diffusion Models](https://mlsanity.com/paper/2406.01062/) (2024)
- [Zero-Shot Styled Text Image Generation, but Make It Autoregressive](https://mlsanity.com/paper/2503.17074/) (2025)
- [AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks](https://mlsanity.com/paper/2201.09390/) (2022)
- [Mimetic Models: Ethical Implications of AI that Acts Like You](https://mlsanity.com/paper/2207.09394/) (2022)
- [Kinetic Typography Diffusion Model](https://mlsanity.com/paper/2407.10476/) (2024)
- [Intelligent Artistic Typography: A Comprehensive Review of Artistic Text Design and Generation](https://mlsanity.com/paper/2407.14774/) (2024)
- [Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing](https://mlsanity.com/paper/2402.03082/) (2024)
- [LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight](https://mlsanity.com/paper/2511.20648/) (2025)
- [GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation](https://mlsanity.com/paper/2207.09649/) (2022)
- [FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework](https://mlsanity.com/paper/2308.02905/) (2023)
- [Rethinking HTG Evaluation: Bridging Generation and Recognition](https://mlsanity.com/paper/2409.02683/) (2024)
- [Detecting Visual Information Manipulation Attacks in Augmented Reality: A Multimodal Semantic Reasoning Approach](https://mlsanity.com/paper/2507.20356/) (2025)
- [Show Me the World in My Language: Establishing the First Baseline for Scene-Text to Scene-Text Translation](https://mlsanity.com/paper/2308.03024/) (2023)
- [Typographic Text Generation with Off-the-Shelf Diffusion Model](https://mlsanity.com/paper/2402.14314/) (2024)
- [StyleTextGen: Style-Conditioned Multilingual Scene Text Generation](https://mlsanity.com/paper/2605.14708/) (2026)
- [Scene Style Text Editing](https://mlsanity.com/paper/2304.10097/) (2023)
- [APRNet: Attention-based Pixel-wise Rendering Network for Photo-Realistic Text Image Generation](https://mlsanity.com/paper/2203.07705/) (2022)
- [Task Grouping for Multilingual Text Recognition](https://mlsanity.com/paper/2210.07423/) (2022)

## Abstract (arXiv)

We present a novel approach for disentangling the content of a text image from all aspects of its appearance. The appearance representation we derive can then be applied to new content, for one-shot transfer of the source style to new content. We learn this disentanglement in a self-supervised manner. Our method processes entire word boxes, without requiring segmentation of text from background, per-character processing, or making assumptions on string lengths. We show results in different text domains which were previously handled by specialized methods, e.g., scene text, handwritten text. To these ends, we make a number of technical contributions: (1) We disentangle the style and content of a textual image into a non-parametric, fixed-dimensional vector. (2) We propose a novel approach inspired by StyleGAN but conditioned over the example style at different resolution and content. (3) We present novel self-supervised training criteria which preserve both source style and target content using a pre-trained font classifier and text recognizer. Finally, (4) we also introduce Imgur5K, a new challenging dataset for handwritten word images. We offer numerous qualitative photo-realistic results of our method. We further show that our method surpasses previous work in quantitative tests on scene text and handwriting datasets, as well as in a user study.