Search papers, labs, and topics across Lattice.
This paper integrates evolutionary search with Wave Function Collapse (WFC) to enhance procedural content generation by evolving the small input examples rather than the complete outputs. The approach leverages WFC as a mapping from genotype to phenotype, allowing for the evaluation of generated levels through domain-specific fitness functions. Results indicate that this method significantly improves generation quality in environments where local relationships dictate properties, although challenges persist in domains reliant on global constraints.
Evolving input examples for Wave Function Collapse can drastically enhance procedural content generation quality, especially in locally structured domains.
Wave Function Collapse (WFC) is a widely used procedural content generation method that learns local adjacency constraints from example inputs to generate larger outputs. In this paper, we explore combining WFC with evolutionary search by evolving the small input examples used by WFC rather than directly evolving complete levels. In this approach, WFC acts as a genotype-to-phenotype mapping. The generated levels are then evaluated through domain-specific fitness functions. We evaluate the method in two domains with different relationships between local and global structure: Maze connectivity maps and Zelda-style dungeon layouts. Our results show that evolutionary optimization over WFC inputs improves generation quality in domains where properties emerge from local relationships, while domains requiring global constraints remain challenging. These findings suggest that evolutionary search can effectively guide WFC generation when target objectives align with local structure.
