Very very cool. I love their approach of looking for similarity metrics that are less sensitive to local misalignment, and this is something I'me very interested in exploring in the future.

I'm not completely convinced by their distinction between "tone-based" and "structure-based", though. When they talk about structure, it seems to primarily mean 'edges'. Instead maybe a more useful distinction would be between "local optimization" (at the level of a single printed character), and optimizing "globally" or over a wider area of the image, and so allowing an iterative optimizer to find a really compact representation.