An Assessment of Shadow Generation by GAN with Depth Images on Non-Planar Backgrounds

Kaito Toyama, Maki Sugimoto

2025

Abstract

We propose the use of a Generative Adversarial Network (GAN) with depth images to generate shadows for virtual objects in mixed reality environments. This approach improves the accuracy of shadow generation process by aligning shadows with non-planar geometries. While traditional methods require detailed lighting and geometry data, recent research has emerged that generates shadows by learning from the image itself, even when such conditions are not fully known. However, these studies are limited to projecting shadows only onto the ground: a planar geometry. Our dataset used for training the GAN, includes depth images allows natural shadow generation in complex environments.

Paper Citation

in Harvard Style

Toyama K. and Sugimoto M. (2025). An Assessment of Shadow Generation by GAN with Depth Images on Non-Planar Backgrounds. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 135-142. DOI: 10.5220/0013188200003912

in Bibtex Style

@conference{visapp25,
author={Kaito Toyama and Maki Sugimoto},
title={An Assessment of Shadow Generation by GAN with Depth Images on Non-Planar Backgrounds},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={135-142},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013188200003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - An Assessment of Shadow Generation by GAN with Depth Images on Non-Planar Backgrounds
SN - 978-989-758-728-3
AU - Toyama K.
AU - Sugimoto M.
PY - 2025
SP - 135
EP - 142
DO - 10.5220/0013188200003912
PB - SciTePress