A Deep Factorization of Style and Structure in Fonts
This addresses typographic analysis for designers and researchers, offering incremental improvements in font reconstruction tasks.
The paper tackled the problem of disentangling content from style in fonts by proposing a deep factorization model, achieving superior performance in reconstructing missing glyphs from unseen fonts compared to baseline and state-of-the-art methods.
We propose a deep factorization model for typographic analysis that disentangles content from style. Specifically, a variational inference procedure factors each training glyph into the combination of a character-specific content embedding and a latent font-specific style variable. The underlying generative model combines these factors through an asymmetric transpose convolutional process to generate the image of the glyph itself. When trained on corpora of fonts, our model learns a manifold over font styles that can be used to analyze or reconstruct new, unseen fonts. On the task of reconstructing missing glyphs from an unknown font given only a small number of observations, our model outperforms both a strong nearest neighbors baseline and a state-of-the-art discriminative model from prior work.