# Learning to Kern: Set-wise Estimation of Optimal Letter Space

arXiv: https://arxiv.org/abs/2402.14313 · HTML: https://mlsanity.com/paper/2402.14313/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [LayoutDM: Discrete Diffusion Model for Controllable Layout Generation](https://mlsanity.com/paper/2303.08137/) (2023)
- [Variational Transformer Networks for Layout Generation](https://mlsanity.com/paper/2104.02416/) (2021)
- [BLT: Bidirectional Layout Transformer for Controllable Layout Generation](https://mlsanity.com/paper/2112.05112/) (2021)
- [Attribute-conditioned Layout GAN for Automatic Graphic Design](https://mlsanity.com/paper/2009.05284/) (2020)
- [LayoutDM: Transformer-based Diffusion Model for Layout Generation](https://mlsanity.com/paper/2305.02567/) (2023)
- [Diverse Multimedia Layout Generation with Multi Choice Learning](https://mlsanity.com/paper/2301.06629/) (2023)

## Built on by (most cited first, 1 of 1)

- [BoundInk: Boundary-Aware Online Handwriting Generation](https://mlsanity.com/paper/2604.02103/) (2026)

## Abstract (arXiv)

Kerning is the task of setting appropriate horizontal spaces for all possible letter pairs of a certain font. One of the difficulties of kerning is that the appropriate space differs for each letter pair. Therefore, for a total of 52 capital and small letters, we need to adjust 52 × 52 = 2704 different spaces. Another difficulty is that there is neither a general procedure nor criterion for automatic kerning; therefore, kerning is still done manually or with heuristics. In this paper, we tackle kerning by proposing two machine-learning models, called pairwise and set-wise models. The former is a simple deep neural network that estimates the letter space for two given letter images. In contrast, the latter is a transformer-based model that estimates the letter spaces for three or more given letter images. For example, the set-wise model simultaneously estimates 2704 spaces for 52 letter images for a certain font. Among the two models, the set-wise model is not only more efficient but also more accurate because its internal self-attention mechanism allows for more consistent kerning for all letters. Experimental results on about 2500 Google fonts and their quantitative and qualitative analyses show that the set-wise model has an average estimation error of only about 5.3 pixels when the average letter space of all fonts and letter pairs is about 115 pixels.