tile2tile: Learning Game Filters for Platformer Style Transfer


  • Anurag Sarkar Northeastern University
  • Seth Cooper Northeastern University




PCGML, Style Transfer, Platformer, Autoencoder, Markov Random Field


We present tile2tile, an approach for style transfer between levels of tile-based platformer games. Our method involves training models that translate levels from a lower-resolution sketch representation based on tile affordances to the original tile representation for a given game. This enables these models, which we refer to as filters, to translate level sketches into the style of a specific game. Moreover, by converting a level of one game into sketch form and then translating the resulting sketch into the tiles of another game, we obtain a method of style transfer between two games. We use Markov random fields and autoencoders for learning the game filters and apply them to demonstrate style transfer between levels of Super Mario Bros, Kid Icarus, Mega Man and Metroid.




How to Cite

Sarkar, A., & Cooper, S. (2022). tile2tile: Learning Game Filters for Platformer Style Transfer. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 18(1), 53-60. https://doi.org/10.1609/aiide.v18i1.21947