Automatic generation of in-vehicle images: StyleGAN-ADA vs. MSG-GAN
Computers and Informatics · 2025
DOI: 10.62189/ci.1261718 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers and Informatics, 2025. Verfasst von Sahar Azadi und 5 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Gefördert von: FCT - Fundação para a Ciência e Tecnologia.
Abstract (Originalsprache)
Deep learning-based methodologies are a key component towards the goal of autonomous driving. For a successful application, these models require a significant amount of training data, which is difficult, time-consuming, and expensive to collect. This study assesses the effectiveness of Generative Adversarial Networks (GANs) in generating high-quality training images for in-vehicle applications using a limited dataset. Two advanced GAN architectures were compared for their ability to produce realistic in-vehicle RGB images. The results showed that the StyleGAN-ADA outperformed the MSG-GAN, generating images with better fidelity and accuracy, making it more suitable for scenarios with limited data. However, challenges such as mode collapse and long training times, particularly for high-resolution images, were identified. The models’ reliance on the quality and diversity of the training dataset also limits their effectiveness in real-world applications. This research highlights the potential of GANs to reduce the lack of data in autonomous driving, pointing to future approaches for optimizing these models.
Förderung
- FCT - Fundação para a Ciência e Tecnologia
Zitieren
APA
Azadi, S., Dixe, S., Leite, J., Borges, J., Queiros, S., & Fonseca, J. (2025). Automatic generation of in-vehicle images: StyleGAN-ADA vs. MSG-GAN. Computers and Informatics. https://doi.org/10.62189/ci.1261718
Vancouver
Azadi S, Dixe S, Leite J, Borges J, Queiros S, Fonseca J. Automatic generation of in-vehicle images: StyleGAN-ADA vs. MSG-GAN. Computers and Informatics. 2025. doi:10.62189/ci.1261718
BibTeX
@article{Azadi2025,
author = {Azadi, Sahar and Dixe, Sandra and Leite, Joao and Borges, Joao and Queiros, Sandro and Fonseca, Jeime},
title = {Automatic generation of in-vehicle images: StyleGAN-ADA vs. MSG-GAN},
journal = {Computers and Informatics},
year = {2025},
doi = {10.62189/ci.1261718}
}
EUVIMED