Wave Function Approximation: Performant Level Generation for Games
Mathias Babin, Michael J. Katchabaw · 2025
This work presents a novel approach to integrating artificial neural networks (ANNs) into the WaveFunctionCollapse (WFC) algorithm for more efficient level generation in games. WFC is a texture synthesis algorithm that has shown promising results for generating textures as well as entire 2D and 3D game environments. This work aims to supplement this algorithm by introducing new methods aimed at its performance, specifically, through the use of AI-based function approximation to relieve the heavy computational needs of its constraint satisfaction steps. We also discuss how we can use the marching squares algorithm to reduce both the input and output space of our model, leading to further performance benefits.