TOAD-GAN: Coherent Style Level Generation from a Single Example
This addresses the need for efficient procedural content generation in game design, though it is incremental as it builds on the SinGAN architecture.
The authors tackled the problem of generating video game levels in a specific style from a single example, achieving state-of-the-art results in modeling patterns and enabling user-controlled generation for coherent layouts.
In this work, we present TOAD-GAN (Token-based One-shot Arbitrary Dimension Generative Adversarial Network), a novel Procedural Content Generation (PCG) algorithm that generates token-based video game levels. TOAD-GAN follows the SinGAN architecture and can be trained using only one example. We demonstrate its application for Super Mario Bros. levels and are able to generate new levels of similar style in arbitrary sizes. We achieve state-of-the-art results in modeling the patterns of the training level and provide a comparison with different baselines under several metrics. Additionally, we present an extension of the method that allows the user to control the generation process of certain token structures to ensure a coherent global level layout. We provide this tool to the community to spur further research by publishing our source code.