mlsanityData to 7 Oct 2026

SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds

arXiv 2201.04494 ↗First posted 12 Jan 2022cs.CV cs.ROcited by 49

Not on the map. Why?

Abstract (arXiv)

With the recent availability and affordability of commercial depth sensors and 3D scanners, an increasing number of 3D (i.e., RGBD, point cloud) datasets have been publicized to facilitate research in 3D computer vision. However, existing datasets either cover relatively small areas or have limited semantic annotations. Fine-grained understanding of urban-scale 3D scenes is still in its infancy. In this paper, we introduce SensatUrban, an urban-scale UAV photogrammetry point cloud dataset consisting of nearly three billion points collected from three UK cities, covering 7.6 km^2. Each point in the dataset has been labelled with fine-grained semantic annotations, resulting in a dataset that is three times the size of the previous existing largest photogrammetric point cloud dataset. In addition to the more commonly encountered categories such as road and vegetation, urban-level categories including rail, bridge, and river are also included in our dataset. Based on this dataset, we further build a benchmark to evaluate the performance of state-of-the-art segmentation algorithms. In particular, we provide a comprehensive analysis and identify several key challenges limiting urban-scale point cloud understanding. The dataset is available at http://point-cloud-analysis.cs.ox.ac.uk.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Builds on 65 of its 105 references that are in the map. First posted on arXiv 12 Jan 2022.

Builds on

65 of 105 references.

References · 65

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  10. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  11. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  12. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
38 more
  1. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  2. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  3. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  4. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  5. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  6. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  7. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  8. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  9. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  10. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  11. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  12. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  13. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  14. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  15. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  16. 2018PCN: Point Completion Networkcited by 382
  17. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  18. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  19. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  20. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  21. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  22. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  23. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  24. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  25. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  26. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  27. 2020A2D2: Audi Autonomous Driving Datasetcited by 189
  28. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  29. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  30. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  31. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  32. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  33. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  34. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  35. 2020SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instancescited by 123
  36. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  37. 2020Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challengescited by 80
  38. 2020Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadwayscited by 77

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 12; 2024: 8; 2025: 11; 2026: 10.

49 papers.

Sort:

By area:

  1. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  2. 2023OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentationcited by 82
  3. 2022STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Datasetcited by 52
  4. 2025Openfly: A comprehensive platform for aerial vision-language navigationcited by 43
  5. 2022EarthNets: Empowering AI in Earth Observationcited by 40
  6. 2024CityNav: A Large-Scale Dataset for Real-World Aerial Navigationcited by 40
  7. 2022No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfacescited by 25
  8. 2023UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentationcited by 24
  9. 2022Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregationcited by 23
  10. 20223DAC: Learning Attribute Compression for Point Cloudscited by 22
  11. 2023Benchmarking the Robustness of LiDAR Semantic Segmentation Modelscited by 18
  12. 2023CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Datacited by 15
37 more
  1. 2023All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentationcited by 13
  2. 2024BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Visioncited by 13
  3. 2025Aerial Vision-and-Language Navigation with Grid-based View Selection and Map Constructioncited by 12
  4. 20243D Question Answering for City Scene Understandingcited by 10
  5. 2025FlySearch: Exploring how vision-language models explorecited by 7
  6. 2022Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Cloudscited by 6
  7. 2024Deep Learning on 3D Semantic Segmentation: A Detailed Reviewcited by 6
  8. 2023Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentationcited by 5
  9. 2026AirNav: A Large-Scale UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructionscited by 5
  10. 2024Pathfinder for Low-altitude Aircraft with Binary Neural Networkcited by 4
  11. 2026VLM-Loc: Localization in Point Cloud Maps via Vision-Language Modelscited by 4
  12. 2023Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Frameworkcited by 3
  13. 2023HRHD-HK: A benchmark dataset of high-rise and high-density urban scenes for 3D semantic segmentation of photogrammetric point cloudscited by 2
  14. 2024Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagerycited by 2
  15. 2025City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learningcited by 2
  16. 2025CitySeg: A 3D Open Vocabulary Semantic Segmentation Foundation Model in City-scale Scenarioscited by 2
  17. 2025SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priorscited by 2
  18. 2026HTNav: A Hybrid Navigation Framework with Tiered Structure for Urban Aerial Vision-and-Language Navigationcited by 2
  19. 2026See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of Viewcited by 2
  20. 2023PVP: Pre-trained Visual Parameter-Efficient Tuningcited by 1
  21. 2024Towards Modality-agnostic Label-efficient Segmentation with Entropy-Regularized Distribution Alignmentcited by 1
  22. 2025CULTURE3D: A Large-Scale and Diverse Dataset of Cultural Landmarks and Terrains for Gaussian-Based Scene Renderingcited by 1
  23. 2025BuildingWorld: A Structured 3D Building Dataset for Urban Foundation Modelscited by 1
  24. 2025Late-decoupled 3D Hierarchical Semantic Segmentation with Semantic Prototype Discrimination based Bi-branch Supervisioncited by 1
  25. 2022TerrainMesh: Metric-Semantic Terrain Reconstruction from Aerial Images Using Joint 2D-3D Learningcited by 0
  26. 2023APNet: Urban-level Scene Segmentation of Aerial Images and Point Cloudscited by 0
  27. 2023Efficient Cloud Pipelines for Neural Radiance Fieldscited by 0
  28. 2023Weakly Supervised Point Cloud Segmentation via Conservative Propagation of Scene-level Labelscited by 0
  29. 2024REPS: Reconstruction-based Point Cloud Samplingcited by 0
  30. 2025PDM-SSD: Single-Stage Three-Dimensional Object Detector With Point Dilationcited by 0
  31. 2025IPCD: Intrinsic Point-Cloud Decompositioncited by 0
  32. 2026Leveraging 2D-VLM for Label-Free 3D Segmentation in Large-Scale Outdoor Scene Understandingcited by 0
  33. 2026Resolving Primitive-Sharing Ambiguity in Long-Tailed TLS-Based Industrial MEP Point Cloud Segmentation via Spatial Context Constraintscited by 0
  34. 2026COSTA: A Cluster-Centric Paradigm for Annotation-Free Open-Set Semantic Segmentation of Aerial Point Clouds with Domain Shiftscited by 0
  35. 2026Polis: 3D Self-Supervision at City Scalecited by 0
  36. 2026VoxelFix: Post-Hoc Semantic Correction of Completed 3D Voxel Mapscited by 0
  37. 2026Map the Possibilities: Spatial Belief Fields for Language-Goal Aerial Navigationcited by 0