Lode Enhancer: Level Co-creation Through Scaling

TL;DR

This paper presents Lode Enhancer, an AI-powered tool that uses neural networks to upscale and co-create 2D game levels at multiple resolutions, facilitating level design through an interactive web editor.

Contribution

It introduces a neural network architecture capable of multi-resolution upscaling and prioritizing rare tiles, integrated into a level editing tool for game design.

Findings

Designers enjoyed using the tool for co-creation.

The tool effectively transfers edits across resolutions.

Feedback suggests potential for further development.

Abstract

We explore AI-powered upscaling as a design assistance tool in the context of creating 2D game levels. Deep neural networks are used to upscale artificially downscaled patches of levels from the puzzle platformer game Lode Runner. The trained networks are incorporated into a web-based editor, where the user can create and edit levels at three different levels of resolution: 4x4, 8x8, and 16x16. An edit at any resolution instantly transfers to the other resolutions. As upscaling requires inventing features that might not be present at lower resolutions, we train neural networks to reproduce these features. We introduce a neural network architecture that is capable of not only learning upscaling but also giving higher priority to less frequent tiles. To investigate the potential of this tool and guide further development, we conduct a qualitative study with 3 designers to understand how they use it. Designers enjoyed co-designing with the tool, liked its underlying concept, and provided feedback for further improvement.