mlsanityData to 7 Oct 2026

Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset

arXiv 2107.04286 ↗First posted 9 Jul 2021cs.CV cs.GRcited by 117

Not on the map. Why?

Abstract (arXiv)

We present UrbanScene3D, a large-scale data platform for research of urban scene perception and reconstruction. UrbanScene3D contains over 128k high-resolution images covering 16 scenes including large-scale real urban regions and synthetic cities with 136 km^2 area in total. The dataset also contains high-precision LiDAR scans and hundreds of image sets with different observation patterns, which provide a comprehensive benchmark to design and evaluate aerial path planning and 3D reconstruction algorithms. In addition, the dataset, which is built on Unreal Engine and Airsim simulator together with the manually annotated unique instance label for each building in the dataset, enables the generation of all kinds of data, e.g., 2D depth maps, 2D/3D bounding boxes, and 3D point cloud/mesh segmentations, etc. The simulator with physical engine and lighting system not only produce variety of data but also enable users to simulate cars or drones in the proposed urban environment for future research.

Key facts. Cited by 117 papers in the map (data through 7 Oct 2026). Builds on 29 of its 49 references that are in the map. First posted on arXiv 9 Jul 2021.

Builds on

29 of 49 references.

References · 29

  1. 2017Mask R-CNNcited by 7,259
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  8. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  9. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  10. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  11. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 477
  12. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
17 more
  1. 2019Tracking without bells and whistlescited by 382
  2. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  3. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  4. 2020Consistent Video Depth Estimationcited by 220
  5. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 214
  6. 2017Cognitive Mapping and Planning for Visual Navigationcited by 209
  7. 2018The Unmanned Aerial Vehicle Benchmark: Object Detection and Trackingcited by 207
  8. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  9. 2018ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Drivingcited by 59
  10. 2019A Behavioral Approach to Visual Navigation with Graph Localization Networkscited by 40
  11. 2020A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Datasetcited by 28
  12. 2020HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structurescited by 28
  13. 2019UAV-GESTURE: A Dataset for UAV Control and Gesture Recognitioncited by 19
  14. 2017Submodular Trajectory Optimization for Aerial 3D Scanningcited by 16
  15. 2020MOR-UAV: A Benchmark Dataset and Baselines for Moving Object Recognition in UAV Videoscited by 15
  16. 2017Plan3D: Viewpoint and Trajectory Optimization for Aerial Multi-View Stereo Reconstructioncited by 5
  17. 2021VGF-Net: Visual-Geometric Fusion Learning for Simultaneous Drone Navigation and Height Mappingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 11; 2024: 21; 2025: 48; 2026: 32.

117 papers.

Sort:

By area:

  1. 2024Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussianscited by 225
  2. 2024A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasetscited by 214
  3. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  4. 2023MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyondcited by 185
  5. 2023CityDreamer: Compositional Generative Model of Unbounded 3D Citiescited by 75
  6. 20253D and 4D World Modeling: A Surveycited by 64
  7. 2023Efficient Large-scale Scene Representation with a Hybrid of High-resolution Grid and Plane Featurescited by 36
  8. 2023GrowSP: Unsupervised Semantic Segmentation of 3D Point Cloudscited by 34
  9. 2024Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenescited by 30
  10. 2023BeyondPixels: A Comprehensive Review of the Evolution of Neural Radiance Fieldscited by 27
  11. 2024Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene Reconstructioncited by 27
  12. 2025CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstructioncited by 26
38 more
  1. 2025UAVScenes: A Multi-Modal Dataset for UAVscited by 26
  2. 20223D Segmentation of Humans in Point Clouds with Synthetic Datacited by 24
  3. 2023UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentationcited by 24
  4. 2023Building3D: An Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Cloudscited by 24
  5. 2024GauStudio: A Modular Framework for 3D Gaussian Splatting and Beyondcited by 24
  6. 2025DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagerycited by 20
  7. 2022LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRFcited by 17
  8. 2025Multi-view Reconstruction via SfM-guided Monocular Depth Estimationcited by 17
  9. 2025Compositional Generative Model of Unbounded 4D Citiescited by 16
  10. 2025EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activitycited by 15
  11. 2022A Review on Viewpoints and Path-planning for UAV-based 3D Reconstructioncited by 14
  12. 2025WorldGrow: Generating Infinite 3D Worldcited by 14
  13. 2024PyGS: Large-scale Scene Representation with Pyramidal 3D Gaussian Splattingcited by 13
  14. 2023SkyScenes: A Synthetic Dataset for Aerial Scene Understandingcited by 12
  15. 2025Neural Radiance Fields for the Real World: A Surveycited by 12
  16. 2024CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstructioncited by 11
  17. 2025OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Renderingcited by 10
  18. 2022Learning Reconstructability for Drone Aerial Path Planningcited by 9
  19. 2025Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Surveycited by 9
  20. 2025BlockGaussian: Efficient Large-Scale Scene Novel View Synthesis via Adaptive Block-Based Gaussian Splattingcited by 8
  21. 2025FIORD: A Fisheye Indoor-Outdoor Dataset with LIDAR Ground Truth for 3D Scene Reconstruction and Benchmarkingcited by 7
  22. 2025FastMap: Revisiting Structure from Motion through First-Order Optimizationcited by 7
  23. 2025Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstructioncited by 7
  24. 2024XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifoldcited by 6
  25. 2025Sat2RealCity: Geometry-Aware and Appearance-Controllable 3D Urban Generation from Satellite Imagerycited by 6
  26. 2023TwinTex: Geometry-aware Texture Generation for Abstracted 3D Architectural Modelscited by 5
  27. 20243D Gaussian Splatting for Large-scale Surface Reconstruction from Aerial Imagescited by 5
  28. 2024DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenescited by 5
  29. 2025TUM2TWIN: Introducing the Large-Scale Multimodal Urban Digital Twin Benchmark Datasetcited by 5
  30. 2025OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspectivecited by 5
  31. 2024GroundUp: Rapid Sketch-Based 3D City Massingcited by 4
  32. 2024SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Datasetcited by 4
  33. 2025CityLoc: 6DoF Pose Distributional Localization for Text Descriptions in Large-Scale Scenes with Gaussian Representationcited by 4
  34. 2025Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splattingcited by 4
  35. 2025Advances in 4D Representation: Geometry, Motion, and Interactioncited by 4
  36. 2026LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditionscited by 4
  37. 2026UrbanGS: A Scalable and Efficient Architecture for Geometrically Accurate Large-Scene Reconstructioncited by 4
  38. 2026Extend3D: Town-Scale 3D Generationcited by 4

50 most cited of 117 All 117 (JSON)