SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes
Not on the map. Why?
Abstract (arXiv)
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/.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 64 references that are in the map. First posted on arXiv 19 Mar 2025.
Builds on
32 of 64 references.
References · 32
- 2023Segment Anythingcited by 8,234
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
- 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
- 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
- 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
- 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
- 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
- 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
- 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
20 more
- 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 406
- 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
- 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 188
- 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
- 2017Deep Extreme Cut: From Extreme Points to Object Segmentationcited by 127
- 2022SimpleClick: Interactive Image Segmentation with Simple Vision Transformerscited by 111
- 2017Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classificationcited by 65
- 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
- 2021The Hessigheim 3D (H3D) Benchmark on Semantic Segmentation of High-Resolution 3D Point Clouds and Textured Meshes from UAV LiDAR and Multi-View-Stereocited by 37
- 2021BuildingNet: Learning to Label 3D Buildingscited by 33
- 2023AGILE3D: Attention Guided Interactive Multi-object 3D Segmentationcited by 33
- 2019DublinCity: Annotated LiDAR Point Cloud and its Applicationscited by 31
- 2020Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor Scenecited by 27
- 2021SUM: A Benchmark Dataset of Semantic Urban Meshescited by 23
- 2022Interactive Object Segmentation in 3D Point Cloudscited by 23
- 2020Semantic Segmentation on Swiss3DCities: A Benchmark Study on Aerial Photogrammetric 3D Pointcloud Datasetcited by 22
- 2022PointVector: A Vector Representation In Point Cloud Analysiscited by 21
- 2024iSeg: Interactive 3D Segmentation via Interactive Attentioncited by 14
- 2022PSSNet: Planarity-sensible Semantic Segmentation of Large-scale Urban Meshescited by 5
- 2018A Data-driven Prior on Facet Orientation for Semantic Mesh Labelingcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.