TOAD-GAN: Coherent Style Level Generation from a Single Example

TL;DR

TOAD-GAN is a novel one-shot GAN-based method for generating coherent, style-matching video game levels from a single example, with user-controlled layout features and state-of-the-art pattern modeling.

Contribution

It introduces TOAD-GAN, a one-shot GAN architecture for token-based level generation, enabling style transfer, arbitrary size levels, and user-controlled layout features.

Findings

Achieves state-of-the-art pattern modeling in level generation.

Can generate levels of arbitrary sizes matching the style of a single example.

Provides user control over token structures for coherent layouts.

Abstract

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.