Font Generation with Missing Impression Labels
This addresses font design automation for designers, but is incremental as it builds on existing GAN methods with label handling improvements.
The paper tackles font generation with ambiguous impression labels by proposing a GAN robust to missing labels, using a co-occurrence-based estimator and label space compressor, and demonstrates high-quality font generation through evaluations.
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.