# CF-Font: Content Fusion for Few-shot Font Generation

arXiv: https://arxiv.org/abs/2303.14017 · HTML: https://mlsanity.com/paper/2303.14017/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 24 Mar 2023.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [Learning to Discover Cross-Domain Relations with Generative Adversarial Networks](https://mlsanity.com/paper/1703.05192/) (2017)
- [Geometric GAN](https://mlsanity.com/paper/1705.02894/) (2017)
- [Few-Shot Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1905.01723/) (2019)
- [Semantic Image Inpainting with Deep Generative Models](https://mlsanity.com/paper/1607.07539/) (2016)
- [One-Sided Unsupervised Domain Mapping](https://mlsanity.com/paper/1706.00826/) (2017)
- [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)
- [Rethinking the Truly Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2006.06500/) (2020)
- [Few-shot Font Generation with Localized Style Representations and Factorization](https://mlsanity.com/paper/2009.11042/) (2020)
- [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)
- [Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation](https://mlsanity.com/paper/2103.16146/) (2021)
- [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)
- [Style and Content Disentanglement in Generative Adversarial Networks](https://mlsanity.com/paper/1811.05621/) (2018)
- [Learning to Write Stylized Chinese Characters by Reading a Handful of Examples](https://mlsanity.com/paper/1712.06424/) (2017)
- [CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator](https://mlsanity.com/paper/2005.12500/) (2020)
- [XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation](https://mlsanity.com/paper/2204.05084/) (2022)
- [Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer](https://mlsanity.com/paper/1904.02296/) (2019)

## Built on by (most cited first, 26 of 26)

- [FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning](https://mlsanity.com/paper/2312.12142/) (2023)
- [Group Diffusion Transformers are Unsupervised Multitask Learners](https://mlsanity.com/paper/2410.15027/) (2024)
- [A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot](https://mlsanity.com/paper/2307.14397/) (2023)
- [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)
- [Predicting the Original Appearance of Damaged Historical Documents](https://mlsanity.com/paper/2412.11634/) (2024)
- [VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization](https://mlsanity.com/paper/2308.14018/) (2023)
- [HFH-Font: Few-shot Chinese Font Synthesis with Higher Quality, Faster Speed, and Higher Resolution](https://mlsanity.com/paper/2410.06488/) (2024)
- [Diff-Oracle: Deciphering Oracle Bone Scripts with Controllable Diffusion Model](https://mlsanity.com/paper/2312.13631/) (2023)
- [Font Style Interpolation with Diffusion Models](https://mlsanity.com/paper/2402.14311/) (2024)
- [CalliffusionV2: Personalized Natural Calligraphy Generation with Flexible Multi-modal Control](https://mlsanity.com/paper/2410.03787/) (2024)
- [FontGuard: A Robust Font Watermarking Approach Leveraging Deep Font Knowledge](https://mlsanity.com/paper/2504.03128/) (2025)
- [MegaHan97K: A Large-Scale Dataset for Mega-Category Chinese Character Recognition with over 97K Categories](https://mlsanity.com/paper/2506.04807/) (2025)
- [MX-Font++: Mixture of Heterogeneous Aggregation Experts for Few-shot Font Generation](https://mlsanity.com/paper/2503.02799/) (2025)
- [From Fragment to One Piece: A Survey on AI-Driven Graphic Design](https://mlsanity.com/paper/2503.18641/) (2025)
- [FontAdapter: Instant Font Adaptation in Visual Text Generation](https://mlsanity.com/paper/2506.05843/) (2025)
- [DA-Font: Few-Shot Font Generation via Dual-Attention Hybrid Integration](https://mlsanity.com/paper/2509.16632/) (2025)
- [DiffInk: Glyph- and Style-Aware Latent Diffusion Transformer for Text to Online Handwriting Generation](https://mlsanity.com/paper/2509.23624/) (2025)
- [Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation](https://mlsanity.com/paper/2601.01593/) (2026)
- [FontCrafter: High-Fidelity Element-Driven Artistic Font Creation with Visual In-Context Generation](https://mlsanity.com/paper/2603.22054/) (2026)
- [Text Image Generation for Low-Resource Languages with Dual Translation Learning](https://mlsanity.com/paper/2409.17747/) (2024)
- [AnyArtisticGlyph: Multilingual Controllable Artistic Glyph Generation](https://mlsanity.com/paper/2504.04743/) (2025)
- [DNA: Dual-branch Network with Adaptation for Open-Set Online Handwriting Generation](https://mlsanity.com/paper/2511.22064/) (2025)
- [InkDiffuser: High-Fidelity One-shot Chinese Calligraphy via Differentiable Morphological Optimization](https://mlsanity.com/paper/2605.05865/) (2026)
- [SmartFont: Dynamic Condition Allocation for Few-Shot Font Generation](https://mlsanity.com/paper/2606.13382/) (2026)
- [Srijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts](https://mlsanity.com/paper/2609.05661/) (2026)

## Abstract (arXiv)

Content and style disentanglement is an effective way to achieve few-shot font generation. It allows to transfer the style of the font image in a source domain to the style defined with a few reference images in a target domain. However, the content feature extracted using a representative font might not be optimal. In light of this, we propose a content fusion module (CFM) to project the content feature into a linear space defined by the content features of basis fonts, which can take the variation of content features caused by different fonts into consideration. Our method also allows to optimize the style representation vector of reference images through a lightweight iterative style-vector refinement (ISR) strategy. Moreover, we treat the 1D projection of a character image as a probability distribution and leverage the distance between two distributions as the reconstruction loss (namely projected character loss, PCL). Compared to L2 or L1 reconstruction loss, the distribution distance pays more attention to the global shape of characters. We have evaluated our method on a dataset of 300 fonts with 6.5k characters each. Experimental results verify that our method outperforms existing state-of-the-art few-shot font generation methods by a large margin. The source code can be found at https://github.com/wangchi95/CF-Font.