Multilayer Map Generation Using Attribute Loss Functions

Date

2023

Authors

Tang, Runze
Sweetser Kyburz, Penny

Journal Title

Journal ISSN

Volume Title

Publisher

ACM

Abstract

Procedural Content Generation via Machine Learning (PCGML) has been studied to generate terrain maps, but many studies focus on height maps and lack human control. We propose a method based on Generative Adversarial Networks (GANs) to generate multilayer maps of terrain with statistical attributes as inputs to introduce more human control. Since the discriminators used in GANs are difficult to evaluate and lack transparency, we propose attribute loss functions, which work as a supervised approach to evaluate the statistical attributes of generated maps directly using differentiable functions for backpropagation. We tested combinations of two model architectures and different conditional normalisation methods and analysed their characteristics. We found that CGAN architecture with batch normalisation worked well in general, while SPADE block introduced more fragments, and channel-wise normalisation satisfied input conditions better but lost distribution diversity and inter-layer relationships.

Description

Keywords

procedural content generation via machine learning, generative adversarial networks, video games, terrain map generation

Citation

Runze Tang and Penny Sweetser. 2023. Multilayer Map Generation Using Attribute Loss Functions. In Foundations of Digital Games 2023 (FDG 2023), April 12–14, 2023, Lisbon, Portugal. ACM, New York, NY, USA, 4 pages. https://doi.org/10.1145/3582437.3587175

Source

Type

Conference paper

Book Title

Foundations of Digital Games 2023 (FDG 2023)

Entity type

Access Statement

Open Access

License Rights

Creative Commons License

Restricted until

Downloads