Reconstructing Existing Levels through Level Inpainting

TL;DR

This paper explores level inpainting in video games, adapting image inpainting techniques with autoencoders and U-net models to reconstruct and extend game levels, showing promising results over baseline methods.

Contribution

It introduces a novel focus on level inpainting within PCGML, adapting image inpainting techniques, and compares two neural network approaches for this task.

Findings

Autoencoder outperforms baseline in inpainting quality

U-net provides detailed level reconstructions

Both methods demonstrate practical viability for level extension

Abstract

Procedural Content Generation (PCG) and Procedural Content Generation via Machine Learning (PCGML) have been used in prior work for generating levels in various games. This paper introduces Content Augmentation and focuses on the subproblem of level inpainting, which involves reconstructing and extending video game levels. Drawing inspiration from image inpainting, we adapt two techniques from this domain to address our specific use case. We present two approaches for level inpainting: an Autoencoder and a U-net. Through a comprehensive case study, we demonstrate their superior performance compared to a baseline method and discuss their relative merits. Furthermore, we provide a practical demonstration of both approaches for the level inpainting task and offer insights into potential directions for future research.