# Total Disentanglement of Font Images into Style and Character Class Features

arXiv: https://arxiv.org/abs/2403.12784 · HTML: https://mlsanity.com/paper/2403.12784/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 19 Mar 2024.

## Builds on (most cited first, 30 of 32)

- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [DRIT++: Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1905.01270/) (2019)
- [On Feature Decorrelation in Self-Supervised Learning](https://mlsanity.com/paper/2105.00470/) (2021)
- [Multi-Content GAN for Few-Shot Font Style Transfer](https://mlsanity.com/paper/1712.00516/) (2017)
- [A Learned Representation for Scalable Vector Graphics](https://mlsanity.com/paper/1904.02632/) (2019)
- [DG-Font: Deformable Generative Networks for Unsupervised Font Generation](https://mlsanity.com/paper/2104.03064/) (2021)
- [Separating Style and Content for Generalized Style Transfer](https://mlsanity.com/paper/1711.06454/) (2017)
- [Image-to-image translation for cross-domain disentanglement](https://mlsanity.com/paper/1805.09730/) (2018)
- [Learning Disentangled Semantic Representation for Domain Adaptation](https://mlsanity.com/paper/2012.11807/) (2020)
- [Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning](https://mlsanity.com/paper/1910.04987/) (2019)
- [FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning](https://mlsanity.com/paper/2312.12142/) (2023)
- [STEFANN: Scene Text Editor using Font Adaptive Neural Network](https://mlsanity.com/paper/1903.01192/) (2019)
- [Few-shot Compositional Font Generation with Dual Memory](https://mlsanity.com/paper/2005.10510/) (2020)
- [Diff-Font: Diffusion Model for Robust One-Shot Font Generation](https://mlsanity.com/paper/2212.05895/) (2022)
- [DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation](https://mlsanity.com/paper/2103.13447/) (2021)
- [Exploring Disentangled Feature Representation Beyond Face Identification](https://mlsanity.com/paper/1804.03487/) (2018)
- [Few-Shot Font Generation by Learning Fine-Grained Local Styles](https://mlsanity.com/paper/2205.09965/) (2022)
- [Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator](https://mlsanity.com/paper/2205.00146/) (2022)
- [Learning to Write Stylized Chinese Characters by Reading a Handful of Examples](https://mlsanity.com/paper/1712.06424/) (2017)
- [DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality](https://mlsanity.com/paper/2303.14585/) (2023)
- [DeepFont: Identify Your Font from An Image](https://mlsanity.com/paper/1507.03196/) (2015)
- [Large-scale Tag-based Font Retrieval with Generative Feature Learning](https://mlsanity.com/paper/1909.02072/) (2019)
- [A Multi-Implicit Neural Representation for Fonts](https://mlsanity.com/paper/2106.06866/) (2021)
- [ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach](https://mlsanity.com/paper/2108.03596/) (2021)
- [TET-GAN: Text Effects Transfer via Stylization and Destylization](https://mlsanity.com/paper/1812.06384/) (2018)
- [XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation](https://mlsanity.com/paper/2204.05084/) (2022)
- [GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks](https://mlsanity.com/paper/1905.12502/) (2019)
- [A Deep Factorization of Style and Structure in Fonts](https://mlsanity.com/paper/1910.00748/) (2019)
- [TE141K: Artistic Text Benchmark for Text Effect Transfer](https://mlsanity.com/paper/1905.03646/) (2019)
- [Shared Latent Space of Font Shapes and Their Noisy Impressions](https://mlsanity.com/paper/2103.12347/) (2021)

## Abstract (arXiv)

In this paper, we demonstrate a total disentanglement of font images. Total disentanglement is a neural network-based method for decomposing each font image nonlinearly and completely into its style and content (i.e., character class) features. It uses a simple but careful training procedure to extract the common style feature from all `A'-`Z' images in the same font and the common content feature from all `A' (or another class) images in different fonts. These disentangled features guarantee the reconstruction of the original font image. Various experiments have been conducted to understand the performance of total disentanglement. First, it is demonstrated that total disentanglement is achievable with very high accuracy; this is experimental proof of the long-standing open question, ``Does `A'-ness exist?'' Hofstadter (1985). Second, it is demonstrated that the disentangled features produced by total disentanglement apply to a variety of tasks, including font recognition, character recognition, and one-shot font image generation. Code is available here: https://github.com/uchidalab/total_disentanglement