mlsanityData to 14 Oct 2026

xBD: A Dataset for Assessing Building Damage from Satellite Imagery

arXiv 1911.09296 ↗First posted 21 Nov 2019cs.CVcited by 139

Not on the map. Why?

Abstract (arXiv)

We present xBD, a new, large-scale dataset for the advancement of change detection and building damage assessment for humanitarian assistance and disaster recovery research. Natural disaster response requires an accurate understanding of damaged buildings in an affected region. Current response strategies require in-person damage assessments within 24-48 hours of a disaster. Massive potential exists for using aerial imagery combined with computer vision algorithms to assess damage and reduce the potential danger to human life. In collaboration with multiple disaster response agencies, xBD provides pre- and post-event satellite imagery across a variety of disaster events with building polygons, ordinal labels of damage level, and corresponding satellite metadata. Furthermore, the dataset contains bounding boxes and labels for environmental factors such as fire, water, and smoke. xBD is the largest building damage assessment dataset to date, containing 850,736 building annotations across 45,362 kmtextsuperscript2 of imagery.

Key facts. Cited by 139 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 20; 2022: 18; 2023: 14; 2024: 23; 2025: 29; 2026: 35.

139 papers.

Sort:

By area:

  1. 2023DiffusionSat: A Generative Foundation Model for Satellite Imagerycited by 131
  2. 2022OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mappingcited by 82
  3. 2021S2Looking: A Satellite Side-Looking Dataset for Building Change Detectioncited by 77
  4. 2021TorchGeo: Deep Learning With Geospatial Datacited by 73
  5. 2021Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagerycited by 64
  6. 2021SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learningcited by 54
  7. 2024GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Taskscited by 51
  8. 2025ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Taskscited by 46
  9. 2025SegEarth-R1: Geospatial Pixel Reasoning via Large Language Modelcited by 42
  10. 2022RescueNet: A High Resolution UAV Semantic Segmentation Benchmark Dataset for Natural Disaster Damage Assessmentcited by 40
  11. 2022EarthNets: Empowering AI in Earth Observationcited by 40
  12. 2024Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation datacited by 39
38 more
  1. 2024Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Modelcited by 37
  2. 2025DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Responsecited by 36
  3. 2024Segment Any Changecited by 35
  4. 2023Physics-Informed Computer Vision: A Review and Perspectivescited by 28
  5. 2022Incidents1M: a large-scale dataset of images with natural disasters, damage, and incidentscited by 26
  6. 2024SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Imagescited by 25
  7. 2022Large-scale Building Damage Assessment using a Novel Hierarchical Transformer Architecture on Satellite Imagescited by 24
  8. 2023What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentationcited by 24
  9. 2023Scalable Multi-Temporal Remote Sensing Change Data Generation via Simulating Stochastic Change Processcited by 22
  10. 2021Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesiscited by 20
  11. 2022Dual-Tasks Siamese Transformer Framework for Building Damage Assessmentcited by 20
  12. 2021BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite Imagescited by 19
  13. 2025DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understandingcited by 18
  14. 2025SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Imagescited by 16
  15. 2021VQA-Aid: Visual Question Answering for Post-Disaster Damage Assessment and Analysiscited by 15
  16. 2026OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agentscited by 15
  17. 2025RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Eventscited by 14
  18. 2024A Change Detection Reality Checkcited by 13
  19. 2023SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing imagescited by 12
  20. 2024Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Surveycited by 12
  21. 2025The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generationcited by 12
  22. 2021The SpaceNet Multi-Temporal Urban Development Challengecited by 10
  23. 2025Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflectioncited by 10
  24. 2022Fast building segmentation from satellite imagery and few local labelscited by 9
  25. 2024CRASAR-U-DROIDs: A Large Scale Benchmark Dataset for Building Alignment and Damage Assessment in Georectified sUAS Imagerycited by 9
  26. 2023Rapid building damage assessment workflow: An implementation for the 2023 Rolling Fork, Mississippi tornado eventcited by 8
  27. 2024Single-Temporal Supervised Learning for Universal Remote Sensing Change Detectioncited by 8
  28. 2025DamageCAT: A Deep Learning Transformer Framework for Typology-Based Post-Disaster Building Damage Categorizationcited by 8
  29. 2025Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Imagescited by 8
  30. 2025GeoLink: Empowering Remote Sensing Foundation Model with OpenStreetMap Datacited by 8
  31. 2026TerraScope: Pixel-Grounded Visual Reasoning for Earth Observationcited by 7
  32. 2026Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systemscited by 6
  33. 2026Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operationscited by 6
  34. 2025TerraGen: A Unified Multi-Task Layout Generation Framework for Remote Sensing Data Augmentationcited by 5
  35. 2021NIDA-CLIFGAN: Natural Infrastructure Damage Assessment through Efficient Classification Combining Contrastive Learning, Information Fusion and Generative Adversarial Networkscited by 4
  36. 2021Fully convolutional Siamese neural networks for buildings damage assessment from satellite imagescited by 4
  37. 2022BLDNet: A Semi-supervised Change Detection Building Damage Framework using Graph Convolutional Networks and Urban Domain Knowledgecited by 4
  38. 2022Supervising Remote Sensing Change Detection Models with 3D Surface Semanticscited by 4

50 most cited of 139 All 139 (JSON)