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
Collections
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
File
Description