首个面向城市网格的部件级语义分割数据集，助力三维场景理解
SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes
- 构建首个城市纹理网格部件级标注数据集，覆盖2.5平方公里
- 支持面与纹理双重标注，提升细粒度语义分割精度
- 适合三维重建、自动驾驶等领域的研究者使用
城市场景分析中的语义分割主要集中在图像或点云，而具备更丰富空间表征的纹理网格仍被忽视。本文提出SUM Parts，首个大规模城市纹理网格部件级语义标注数据集，覆盖约2.5平方公里，包含21类语义标签。数据集通过自研标注工具创建，支持基于面和纹理的交互式标注，实现高效选择。同时，我们在该数据集上对3D语义分割与交互标注方法进行了全面评估。项目主页见 https://tudelft3d.github.io/SUMParts/。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。