mlsanityData to 7 Oct 2026

All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes

arXiv 2312.12176 ↗First posted 19 Dec 2023cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

We introduce UrbanSyn, a photorealistic dataset acquired through semi-procedurally generated synthetic urban driving scenarios. Developed using high-quality geometry and materials, UrbanSyn provides pixel-level ground truth, including depth, semantic segmentation, and instance segmentation with object bounding boxes and occlusion degree. It complements GTAV and Synscapes datasets to form what we coin as the 'Three Musketeers'. We demonstrate the value of the Three Musketeers in unsupervised domain adaptation for image semantic segmentation. Results on real-world datasets, Cityscapes, Mapillary Vistas, and BDD100K, establish new benchmarks, largely attributed to UrbanSyn. We make UrbanSyn openly and freely accessible (www.urbansyn.org).

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 51 of its 74 references that are in the map. First posted on arXiv 19 Dec 2023.

Builds on

51 of 74 references.

References · 51

  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  3. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  5. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  6. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  7. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  8. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  9. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  10. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  11. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 593
  12. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
38 more
  1. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 517
  2. 2019Confidence Regularized Self-Trainingcited by 418
  3. 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
  4. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  5. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  6. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  7. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  8. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  9. 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
  10. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  11. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  12. 2016Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?cited by 194
  13. 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
  14. 2019Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approachescited by 181
  15. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
  16. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  17. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  18. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  19. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  20. 2019Meta-Sim: Learning to Generate Synthetic Datasetscited by 128
  21. 2019Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentationcited by 126
  22. 2020Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentationcited by 126
  23. 2021Simple multi-dataset detectioncited by 126
  24. 2020A Survey of End-to-End Driving: Architectures and Training Methodscited by 123
  25. 2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
  26. 2018Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsingcited by 105
  27. 2019All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentationcited by 104
  28. 2018Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Datacited by 94
  29. 2019Multi-source Domain Adaptation for Semantic Segmentationcited by 74
  30. 2021DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentationcited by 45
  31. 2021Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentationcited by 44
  32. 2020Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentationcited by 41
  33. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  34. 2019Critically Examining the "Neural Hype": Weak Baselines and the Additivity of Effectiveness Gains from Neural Ranking Modelscited by 24
  35. 2020mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasetscited by 19
  36. 2021Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptationcited by 13
  37. 2021Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptationcited by 11
  38. 2022Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Modelscited by 7

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 10; 2026: 22.

40 papers.

Sort:

By area:

  1. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  2. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  3. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformerscited by 47
  4. 2025GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priorscited by 36
  5. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  6. 2025Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Modelscited by 23
  7. 2024SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learningcited by 22
  8. 2026InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fieldscited by 19
  9. 2026MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sourcescited by 10
  10. 2025FastMap: Revisiting Structure from Motion through First-Order Optimizationcited by 7
  11. 2026PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimationcited by 5
  12. 2026MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinementcited by 4
28 more
  1. 2026Large Depth Completion Model from Sparse Observationscited by 3
  2. 2025Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Modelscited by 2
  3. 2026Pixel-Perfect Visual Geometry Estimationcited by 2
  4. 2026DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimationcited by 2
  5. 2026Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridgingcited by 2
  6. 2026SurGe: Improved Surface Geometry in Point Mapscited by 2
  7. 2026FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometrycited by 2
  8. 2026PixRestore: Unified Image Restoration via Pixel Diffusion Transformercited by 2
  9. 2024UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentationcited by 1
  10. 2024Divide, Ensemble and Conquer: The Last Mile on Unsupervised Domain Adaptation for Semantic Segmentationcited by 1
  11. 2024AI-Powered CPS-Enabled Vulnerable-User-Aware Urban Transportation Digital Twin: Methods and Applicationscited by 1
  12. 2025FedS2R: One-Shot Federated Domain Generalization for Synthetic-to-Real Semantic Segmentation in Autonomous Drivingcited by 1
  13. 2026Learning Image-Adaptive Scale Fields for Metric Depth Recoverycited by 1
  14. 2026PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimationcited by 1
  15. 2026OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenescited by 1
  16. 2026Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attentioncited by 1
  17. 2026OmniPoint: Universal Monocular Metric Pointcloud from Any Cameracited by 1
  18. 2024Back2Color: Domain-Adaptive Synthetic-to-Real Monocular Depth Estimation for Dynamic Traffic Scenescited by 0
  19. 2024A Study on Unsupervised Domain Adaptation for Semantic Segmentation in the Era of Vision-Language Modelscited by 0
  20. 2025Research on Driving Scenario Technology Based on Multimodal Large Lauguage Model Optimizationcited by 0
  21. 2025IELDG: Suppressing Domain-Specific Noise with Inverse Evolution Layers for Domain Generalized Semantic Segmentationcited by 0
  22. 2025A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentationcited by 0
  23. 2026Language-Grounded Multi-Domain Image Translation via Semantic Difference Guidancecited by 0
  24. 2026Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentationcited by 0
  25. 2026RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentationcited by 0
  26. 2026ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioningcited by 0
  27. 2026Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensorscited by 0
  28. 2026MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentationcited by 0