Font Generation with Missing Impression Labels

TL;DR

This paper introduces a robust font generation model using GANs that effectively handles missing impression labels by estimating and compressing impression label space, resulting in high-quality font synthesis.

Contribution

It proposes a novel approach combining co-occurrence-based label estimation and impression space compression to improve font generation with incomplete label data.

Findings

The model generates high-quality fonts with missing impression labels.

Qualitative and quantitative evaluations confirm the effectiveness of the approach.

The method outperforms baseline models in handling incomplete label data.

Abstract

Our goal is to generate fonts with specific impressions, by training a generative adversarial network with a font dataset with impression labels. The main difficulty is that font impression is ambiguous and the absence of an impression label does not always mean that the font does not have the impression. This paper proposes a font generation model that is robust against missing impression labels. The key ideas of the proposed method are (1)a co-occurrence-based missing label estimator and (2)an impression label space compressor. The first is to interpolate missing impression labels based on the co-occurrence of labels in the dataset and use them for training the model as completed label conditions. The second is an encoder-decoder module to compress the high-dimensional impression space into low-dimensional. We proved that the proposed model generates high-quality font images using multi-label data with missing labels through qualitative and quantitative evaluations.