Lightweight Transformer Occupancy Networks for 3D Virtual Object Reconstruction

Claudia Melis Tonti, Irene Amerini

2025

Abstract

The increasing demand for edge devices highlights the necessity for modern technologies to be adaptable to general-purpose hardware. Specifically, in fields like augmented reality, virtual reality, and computer graphics, reconstructing 3D objects from sparse point clouds is highly computationally intensive, presenting challenges for execution on embedded devices. In previous works, the speed of 3D mesh generation has been prioritized with respect to preserving a high level of detail. Our focus in this work is to enhance the speed of the inference in order to get closer to real-time mesh generation.

Paper Citation

in Harvard Style

Tonti C. and Amerini I. (2025). Lightweight Transformer Occupancy Networks for 3D Virtual Object Reconstruction. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP; ISBN 978-989-758-728-3, SciTePress, pages 408-414. DOI: 10.5220/0013377400003912

in Bibtex Style

@conference{grapp25,
author={Claudia Tonti and Irene Amerini},
title={Lightweight Transformer Occupancy Networks for 3D Virtual Object Reconstruction},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP},
year={2025},
pages={408-414},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013377400003912},
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 1: GRAPP
TI - Lightweight Transformer Occupancy Networks for 3D Virtual Object Reconstruction
SN - 978-989-758-728-3
AU - Tonti C.
AU - Amerini I.
PY - 2025
SP - 408
EP - 414
DO - 10.5220/0013377400003912
PB - SciTePress