Skip to yearly menu bar Skip to main content


Poster

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

Weixiao Gao · Liangliang Nan · Hugo Ledoux

ExHall D Poster #329
[ ] [ Project Page ]
Sun 15 Jun 8:30 a.m. PDT — 10:30 a.m. PDT

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 \textbf{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.

Live content is unavailable. Log in and register to view live content