SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes
This addresses a gap in urban scene analysis for researchers and practitioners by providing a new benchmark, but it is incremental as it focuses on dataset creation rather than novel methods.
The paper tackles the lack of part-level semantic segmentation datasets for urban textured meshes by introducing SUM Parts, a large-scale dataset covering about 2.5 km2 with 21 classes, and provides evaluations of existing methods on it.
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/.