Detecting Corruption in Real Video Game Graphics using Deep Convolutional Neural Networks

Matthieu Chan Chee, Vinay Pandit, Max Kiehn

2022

Abstract

Early detection of video game display corruption is essential to maintain the highest quality standards and to reduce the time to market of new GPUs targeted for the gaming industry. This paper presents a Deep Learning approach to automate gameplay corruption detection, which otherwise requires labor-intensive manual inspection. Unlike prior efforts which are reliant on synthetically generated corrupted images, we collected real-world examples of corrupted images from over 50 game titles. We trained an EfficientNet to classify input game frames as corrupted or golden using a two-stage training strategy and extensive hyperparameter search. Our method was able to accurately detect a variety of geometric, texture, and color corruptions with a precision of 0.989 and recall of 0.888.

Paper Citation

in Harvard Style

Chan Chee M., Pandit V. and Kiehn M. (2022). Detecting Corruption in Real Video Game Graphics using Deep Convolutional Neural Networks. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 901-908. DOI: 10.5220/0010788900003124

in Bibtex Style

@conference{visapp22,
author={Matthieu Chan Chee and Vinay Pandit and Max Kiehn},
title={Detecting Corruption in Real Video Game Graphics using Deep Convolutional Neural Networks},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={901-908},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010788900003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Detecting Corruption in Real Video Game Graphics using Deep Convolutional Neural Networks
SN - 978-989-758-555-5
AU - Chan Chee M.
AU - Pandit V.
AU - Kiehn M.
PY - 2022
SP - 901
EP - 908
DO - 10.5220/0010788900003124
PB - SciTePress