NIV: Neural Axis Variations for Variable Font Generation
Quick Answer
This paper shows that NIV (Neural Axis Variations) automates the conversion of static fonts into variable fonts by predicting per-point displacements on glyph outlines.
Quick Take
Trained on over one million tuples from Google Fonts, it supports multi-axis variations and generalizes across various styles and handwriting inputs, with outputs compatible with existing rendering engines.
Key Points
- NIV predicts per-point displacements for glyph outlines to create variable fonts.
- Trained on a dataset of over one million variation tuples from Google Fonts.
- Supports consistent multi-axis variation within a unified framework.
- Generalizes across unseen code points and high-complexity CJK glyphs.
- Outputs are standard variable font files compatible with existing rendering engines.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Variable fonts enable continuous variation of glyph geometry along semantic design axes such as weight, width, slant, and optical size. However, constructing a variable font from a static font remains a labor-intensive process requiring expert typographic design and manual specification of glyph variation data. We introduce NIV (Neural Axis Variations), a method that automatically converts a static font into a fully functional variable font. Given glyph outlines and a set of desired design axes, NIV predicts per-point displacements. The model operates directly on vector glyph geometry and employs a novel Property Embedding mechanism that captures interactions between multiple axes, enabling consistent multi-axis variation within a unified framework. We train NIV on a newly constructed dataset derived from variable Google Fonts, comprising over one million variation tuples. The resulting model generalizes across unseen code points, unseen font styles, high-complexity CJK glyphs, and even out-of-distribution handwriting inputs. The generated outputs are standard variable font files supporting continuous interpolation via existing rendering engines. To facilitate research, we release the dataset, the complete training and inference implementation, and trained models at this https URL. Beyond typography, our approach demonstrates how structured geometric objects with continuous parametric variation can be synthesized using neural deformations.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.05261 [cs.CV] |
| (or arXiv:2606.05261v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2606.05261 arXiv-issued DOI via DataCite |
Submission history
From: Nadav Benedek [view email]
[v1]
Wed, 3 Jun 2026 16:17:43 UTC (6,382 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.