Geometry and texture completion of partially scanned 3d objects
Abstract
This work aims to improve the geometry and texture completion of partially scanned 3D objects in indoor environments by identifying limitations in existing completion techniques, including a lack of material awareness, insufficient fine detailing methods, and a scarcity of textured 3D object datasets. A novel completion pipeline is proposed that improves both the geometry and texture completion process.
Workflow
Bibtex
@conference{grapp25,
author={Jelle Vermandere and Maarten Bassier and Maarten Vergauwen},
title={Geometry and Texture Completion of Partially Scanned 3D Objects Through Material Segmentation},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - GRAPP},
year={2025},
pages={193-202},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013120000003912},
isbn={978-989-758-728-3},
issn={2184-4321},
}