SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Gao, Weixiao, Nan, Liangliang, Ledoux, Hugo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908276625506304
author Gao, Weixiao
Nan, Liangliang
Ledoux, Hugo
author_facet Gao, Weixiao
Nan, Liangliang
Ledoux, Hugo
contents Semantic segmentation in urban scene analysis has mainly focused on images or point clouds, while textured meshes - offering richer spatial representation - remain underexplored. This paper introduces SUM Parts, the first large-scale dataset for urban textured meshes with part-level semantic labels, covering about 2.5 km2 with 21 classes. The dataset was created using our own annotation tool, which supports both face- and texture-based annotations with efficient interactive selection. We also provide a comprehensive evaluation of 3D semantic segmentation and interactive annotation methods on this dataset. Our project page is available at https://tudelft3d.github.io/SUMParts/.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15300
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes
Gao, Weixiao
Nan, Liangliang
Ledoux, Hugo
Computer Vision and Pattern Recognition
Semantic segmentation in urban scene analysis has mainly focused on images or point clouds, while textured meshes - offering richer spatial representation - remain underexplored. This paper introduces SUM Parts, the first large-scale dataset for urban textured meshes with part-level semantic labels, covering about 2.5 km2 with 21 classes. The dataset was created using our own annotation tool, which supports both face- and texture-based annotations with efficient interactive selection. We also provide a comprehensive evaluation of 3D semantic segmentation and interactive annotation methods on this dataset. Our project page is available at https://tudelft3d.github.io/SUMParts/.
title SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.15300