# MX-Font++: Mixture of Heterogeneous Aggregation Experts for Few-shot Font Generation

arXiv: https://arxiv.org/abs/2503.02799 · HTML: https://mlsanity.com/paper/2503.02799/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 4 Mar 2025.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 24 of 24)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Few-Shot Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1905.01723/) (2019)
- [Splicing ViT Features for Semantic Appearance Transfer](https://mlsanity.com/paper/2201.00424/) (2022)
- [Multi-Content GAN for Few-Shot Font Style Transfer](https://mlsanity.com/paper/1712.00516/) (2017)
- [SVTR: Scene Text Recognition with a Single Visual Model](https://mlsanity.com/paper/2205.00159/) (2022)
- [TextScanner: Reading Characters in Order for Robust Scene Text Recognition](https://mlsanity.com/paper/1912.12422/) (2019)
- [Separating Style and Content for Generalized Style Transfer](https://mlsanity.com/paper/1711.06454/) (2017)
- [Scene Text Recognition from Two-Dimensional Perspective](https://mlsanity.com/paper/1809.06508/) (2018)
- [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)
- [Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts](https://mlsanity.com/paper/2104.00887/) (2021)
- [Few-shot Compositional Font Generation with Dual Memory](https://mlsanity.com/paper/2005.10510/) (2020)
- [SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models](https://mlsanity.com/paper/2107.09313/) (2021)
- [On Vocabulary Reliance in Scene Text Recognition](https://mlsanity.com/paper/2005.03959/) (2020)
- [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)
- [Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis](https://mlsanity.com/paper/1706.08789/) (2017)
- [Learning to Write Stylized Chinese Characters by Reading a Handful of Examples](https://mlsanity.com/paper/1712.06424/) (2017)
- [CF-Font: Content Fusion for Few-shot Font Generation](https://mlsanity.com/paper/2303.14017/) (2023)
- [DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training](https://mlsanity.com/paper/2408.00355/) (2024)
- [Intelligent Artistic Typography: A Comprehensive Review of Artistic Text Design and Generation](https://mlsanity.com/paper/2407.14774/) (2024)
- [FontTransformer: Few-shot High-resolution Chinese Glyph Image Synthesis via Stacked Transformers](https://mlsanity.com/paper/2210.06301/) (2022)
- [Weakly Supervised Scene Text Generation for Low-resource Languages](https://mlsanity.com/paper/2306.14269/) (2023)

## Built on by (most cited first, 2 of 2)

- [Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models](https://mlsanity.com/paper/2509.13836/) (2025)
- [InkDiffuser: High-Fidelity One-shot Chinese Calligraphy via Differentiable Morphological Optimization](https://mlsanity.com/paper/2605.05865/) (2026)

## Abstract (arXiv)

Few-shot Font Generation (FFG) aims to create new font libraries using limited reference glyphs, with crucial applications in digital accessibility and equity for low-resource languages, especially in multilingual artificial intelligence systems. Although existing methods have shown promising performance, transitioning to unseen characters in low-resource languages remains a significant challenge, especially when font glyphs vary considerably across training sets. MX-Font considers the content of a character from the perspective of a local component, employing a Mixture of Experts (MoE) approach to adaptively extract the component for better transition. However, the lack of a robust feature extractor prevents them from adequately decoupling content and style, leading to sub-optimal generation results. To alleviate these problems, we propose Heterogeneous Aggregation Experts (HAE), a powerful feature extraction expert that helps decouple content and style downstream from being able to aggregate information in channel and spatial dimensions. Additionally, we propose a novel content-style homogeneity loss to enhance the untangling. Extensive experiments on several datasets demonstrate that our MX-Font++ yields superior visual results in FFG and effectively outperforms state-of-the-art methods. Code and data are available at https://github.com/stephensun11/MXFontpp.