Overview
Atlas is both a theory of artificial creativity and an application of that theory as a scene-generator for 2D games. Given an example level, Atlas reverse-engineers its characteristic style and generates additional levels in that style. Atlas builds upon existing research at the intersection of Computational Creativity and Procedural Content Generation. The defining characteristic of Atlas is that it does not require massive quantities of labeled training data, processing power, or time. Atlas learns style from only a single unlabeled example and is efficient enough to run in real-time.
Atlas is being developed by Martin Mumford, who you can contact for more information: (arcanemx at gmail.com)
Methodology
High-level explanations of the theory and process by which Atlas creates
Progress
For tracking purposes, I'm keeping status updates and progress reports:
Results
Source
Atlas is written in Swift for MacOS, and its source can be found here