mlsanityData to 7 Oct 2026

SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery

arXiv 2406.18151 ↗First posted 26 Jun 2024cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Global semantic 3D understanding from single-view high-resolution remote sensing (RS) imagery is crucial for Earth Observation (EO). However, this task faces significant challenges due to the high costs of annotations and data collection, as well as geographically restricted data availability. To address these challenges, synthetic data offer a promising solution by being easily accessible and thus enabling the provision of large and diverse datasets. We develop a specialized synthetic data generation pipeline for EO and introduce SynRS3D, the largest synthetic RS 3D dataset. SynRS3D comprises 69,667 high-resolution optical images that cover six different city styles worldwide and feature eight land cover types, precise height information, and building change masks. To further enhance its utility, we develop a novel multi-task unsupervised domain adaptation (UDA) method, RS3DAda, coupled with our synthetic dataset, which facilitates the RS-specific transition from synthetic to real scenarios for land cover mapping and height estimation tasks, ultimately enabling global monocular 3D semantic understanding based on synthetic data. Extensive experiments on various real-world datasets demonstrate the adaptability and effectiveness of our synthetic dataset and proposed RS3DAda method. SynRS3D and related codes will be available.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 63 of its 129 references that are in the map. First posted on arXiv 26 Jun 2024.

Builds on

63 of 129 references.

References · 63

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2023GPT-4 Technical Reportcited by 18,132
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  9. 2021Vision Transformers for Dense Predictioncited by 1,789
  10. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  11. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  12. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
38 more
  1. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  2. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  3. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  4. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  5. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  6. 2019Confidence Regularized Self-Trainingcited by 418
  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. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 276
  10. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 259
  11. 2022A Transformer-Based Siamese Network for Change Detectioncited by 243
  12. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  13. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  14. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  15. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 176
  16. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
  17. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  18. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  19. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  20. 2018Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Modelscited by 118
  21. 2024ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Modelcited by 118
  22. 2020CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistencycited by 107
  23. 2018Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsingcited by 105
  24. 2019Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approachcited by 103
  25. 2018Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understandingcited by 98
  26. 2019DADA: Depth-aware Domain Adaptation in Semantic Segmentationcited by 97
  27. 2019Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Modelcited by 84
  28. 2022OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mappingcited by 80
  29. 2018T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Taskscited by 70
  30. 2019Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimationcited by 61
  31. 2023Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networkscited by 55
  32. 2020RarePlanes: Synthetic Data Takes Flightcited by 48
  33. 2020Semantic Change Detection with Asymmetric Siamese Networkscited by 31
  34. 2021Self-supervised Learning of Depth Inference for Multi-view Stereocited by 28
  35. 2020DESC: Domain Adaptation for Depth Estimation via Semantic Consistencycited by 25
  36. 2020StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardizationcited by 23
  37. 2020The Synthinel-1 dataset: a collection of high resolution synthetic overhead imagery for building segmentationcited by 19
  38. 2023SyntheWorld: A Large-Scale Synthetic Dataset for Land Cover Mapping and Building Change Detectioncited by 19

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 3.

9 papers.

  1. 2024CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentationcited by 27
  2. 2025Enhancing Monocular Height Estimation via Sparse LiDAR-Guided Correctioncited by 4
  3. 2025Synthetic Data Matters: Re-training with Geo-typical Synthetic Labels for Building Detectioncited by 2
  4. 2025TSE-Net: Semi-supervised Monocular Height Estimation from Single Remote Sensing Imagescited by 1
  5. 2025FOD-S2R: A FOD Dataset for Sim2Real Transfer Learning based Object Detectioncited by 1
  6. 2025Enhancing Monocular Height Estimation via Weak Supervision from Imperfect Labelscited by 0
  7. 2026Test-Time Adaptation for Height Completion via Self-Supervised ViT Features and Monocular Foundation Modelscited by 0
  8. 2026Rapid Debris-Volume Estimation from Post-Hurricane Aerial Imagerycited by 0
  9. 2026SatUnreal: A High-Precision Synthetic Dataset for Satellite Stereo Matching via Unreal Enginecited by 0