Font Shape-to-Impression Translation
This work addresses font design and analysis for designers and typographers, but it is incremental as it applies existing Transformer methods to a new domain.
The paper tackled the problem of analyzing how local parts of fonts contribute to specific impressions by using Transformer-based methods for multi-label classification and translation, achieving more accurate estimation of font impressions compared to other approaches.
Different fonts have different impressions, such as elegant, scary, and cool. This paper tackles part-based shape-impression analysis based on the Transformer architecture, which is able to handle the correlation among local parts by its self-attention mechanism. This ability will reveal how combinations of local parts realize a specific impression of a font. The versatility of Transformer allows us to realize two very different approaches for the analysis, i.e., multi-label classification and translation. A quantitative evaluation shows that our Transformer-based approaches estimate the font impressions from a set of local parts more accurately than other approaches. A qualitative evaluation then indicates the important local parts for a specific impression.