Scalable Font Reconstruction with Dual Latent Manifolds
This addresses font reconstruction and generalization for typography applications, with incremental improvements in scalability and loss design.
The paper tackles font reconstruction by learning disentangled manifolds for font style and character shape, enabling generalization to unseen characters and scaling to more character types than previous methods. It demonstrates favorable performance compared to modern style transfer systems on multilingual datasets.
We propose a deep generative model that performs typography analysis and font reconstruction by learning disentangled manifolds of both font style and character shape. Our approach enables us to massively scale up the number of character types we can effectively model compared to previous methods. Specifically, we infer separate latent variables representing character and font via a pair of inference networks which take as input sets of glyphs that either all share a character type, or belong to the same font. This design allows our model to generalize to characters that were not observed during training time, an important task in light of the relative sparsity of most fonts. We also put forward a new loss, adapted from prior work that measures likelihood using an adaptive distribution in a projected space, resulting in more natural images without requiring a discriminator. We evaluate on the task of font reconstruction over various datasets representing character types of many languages, and compare favorably to modern style transfer systems according to both automatic and manually-evaluated metrics.