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

Weixiao Gao, Liangliang Nan, Hugo Ledoux

CVPR 2025 pp. 24474-24484

doi:10.1109/CVPR52734.2025.02279 /cvpr/2025/gao2025cvpr-sum/

Abstract

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 2.5km^2 with 21 classes. The dataset was created using our designed annotation tool, supporting 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.

PDF CVPR Semantic Scholar

Cite

Text

Gao et al. "SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.02279

Markdown

[Gao et al. "SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/gao2025cvpr-sum/) doi:10.1109/CVPR52734.2025.02279

BibTeX

@inproceedings{gao2025cvpr-sum,
  title     = {{SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes}},
  author    = {Gao, Weixiao and Nan, Liangliang and Ledoux, Hugo},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2025},
  pages     = {24474-24484},
  doi       = {10.1109/CVPR52734.2025.02279},
  url       = {https://mlanthology.org/cvpr/2025/gao2025cvpr-sum/}
}