Towards Generating 3D City Models with GAN and Computer Vision Methods

Sarun Poolkrajang, Anand Bhojan

2024

Abstract

City generation for video games is a resource and time-consuming task. With the increasing popularity of open-world games, studies on building virtual environments have become increasingly important for the game research community and industry. The game development team must engage in urban planning, designate important locations, create population assets, integrate game design, and assemble these elements into a cohesive-looking city. Based on our limited knowledge and survey, we are the first to propose a holistic approach that integrates all features in generating a city, including the natural features surrounding it. We employ a generative adversarial network architecture to create a realistic layout of an entire city from scratch. Subsequently, we utilize classical computer vision techniques to post-process the layout into separate features. The chosen model is a simple Convolutional GAN, trained on a modest dataset of 2x2 km² snippets from over two thousand cities around the world. Although the method is somewhat constrained by the resolution of the images, the results indicate that it can serve as a solid foundation for building realistic 3D cities.

Paper Citation

in Harvard Style

Poolkrajang S. and Bhojan A. (2024). Towards Generating 3D City Models with GAN and Computer Vision Methods. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP; ISBN 978-989-758-679-8, SciTePress, pages 211-219. DOI: 10.5220/0012315000003660

in Bibtex Style

@conference{grapp24,
author={Sarun Poolkrajang and Anand Bhojan},
title={Towards Generating 3D City Models with GAN and Computer Vision Methods},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP},
year={2024},
pages={211-219},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012315000003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP
TI - Towards Generating 3D City Models with GAN and Computer Vision Methods
SN - 978-989-758-679-8
AU - Poolkrajang S.
AU - Bhojan A.
PY - 2024
SP - 211
EP - 219
DO - 10.5220/0012315000003660
PB - SciTePress