Vermandere, JelleBassier, MaartenCuypers, SuzannaVergauwen, MaartenHunter, DavidSlingsby, Aidan2024-09-092024-09-092024978-3-03868-249-3https://doi.org/10.2312/cgvc.20241221https://diglib.eg.org/handle/10.2312/cgvc20241221This work aims to improve texture inpainting following clutter removal in scanned indoor meshes. This is achieved through a new UV mapping pre-processing step that leverages semantic information from indoor scenes to more accurately align the UV islands with the 3D representations of distinct structural elements, such as walls and floors. Semantic UV Mapping enhances traditional UV unwrapping algorithms by incorporating not only geometric features but also visual features derived from the existing texture. This segmentation improves UV mapping and simultaneously simplifies the 3D geometric reconstruction of the scene after the removal of loose objects. Each segmented element can then be reconstructed separately, using the boundary conditions of the adjacent elements. Since this is performed as a pre-processing step, other specialized methods for geometric and texture reconstruction can be employed in the future to further enhance the results.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Mesh geometry models; TexturingComputing methodologies → Mesh geometry modelsTexturing10.2312/cgvc.202412215 pages