BevGAN: Generative Fisheye Cross-View Transformers

Rania Benaissa, Antonyo Musabini, Rachid Benmokhtar, Manikandan Bakthavatchalam, Xavier Perrotton

2025

Abstract

Current parking assistance and monitoring systems synthesize Bird Eye View (BEV) images to improve drivers visibility. These BEV images are created using a popular perspective transform called Inverse Perspective Mapping (IPM), which projects pixels of surround-view images captured by onboard fisheye cameras onto a flat plane. However, IPM faces challenges in accurately representing objects with varying heights and seamlessly stitching together the projected surround-views due to its reliance on rigid geometric transformations. To address these limitations, we present BevGAN, a novel geometry-guided Conditional Generative Adversarial Networks (cGANs) model that combines multi-scale discriminators along with a transformers-based generator that leverages fisheye cameras calibration and attention-mechanisms to implicitly model geometrical transformations between the views. Experimental results demonstrate that BevGAN outperforms IPM and state-of-the-art cross-view image generation methods in terms of image fidelity and quality. Compared to IPM, we report an improvement of +6.2db on PSNR and +170% on MS-SSIM when evaluated on a synthetic dataset depicting both parking and driving scenarios. Furthermore, the generalization ability of BevGAN on real-world fisheye images is also demonstrated through zero-shot inference.

Paper Citation

in Harvard Style

Benaissa R., Musabini A., Benmokhtar R., Bakthavatchalam M. and Perrotton X. (2025). BevGAN: Generative Fisheye Cross-View Transformers. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 153-163. DOI: 10.5220/0013122200003890

in Bibtex Style

@conference{icaart25,
author={Rania Benaissa and Antonyo Musabini and Rachid Benmokhtar and Manikandan Bakthavatchalam and Xavier Perrotton},
title={BevGAN: Generative Fisheye Cross-View Transformers},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={153-163},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013122200003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - BevGAN: Generative Fisheye Cross-View Transformers
SN - 978-989-758-737-5
AU - Benaissa R.
AU - Musabini A.
AU - Benmokhtar R.
AU - Bakthavatchalam M.
AU - Perrotton X.
PY - 2025
SP - 153
EP - 163
DO - 10.5220/0013122200003890
PB - SciTePress