mlsanityData to 14 Oct 2026

GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis

arXiv 2404.06637 ↗First posted 9 Apr 2024cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

We present GeoSynth, a model for synthesizing satellite images with global style and image-driven layout control. The global style control is via textual prompts or geographic location. These enable the specification of scene semantics or regional appearance respectively, and can be used together. We train our model on a large dataset of paired satellite imagery, with automatically generated captions, and OpenStreetMap data. We evaluate various combinations of control inputs, including different types of layout controls. Results demonstrate that our model can generate diverse, high-quality images and exhibits excellent zero-shot generalization. The code and model checkpoints are available at https://github.com/mvrl/GeoSynth.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 49 of its 59 references that are in the map. First posted on arXiv 9 Apr 2024.

Builds on

49 of 59 references.

References · 49

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023Segment Anythingcited by 8,234
  5. 2023Visual Instruction Tuningcited by 7,869
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  9. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  10. 2017Neural Discrete Representation Learningcited by 4,712
  11. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  12. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
37 more
  1. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  2. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  3. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  4. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,178
  5. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,106
  6. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 906
  7. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 590
  8. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 536
  9. 2023BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editingcited by 442
  10. 2022SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagerycited by 408
  11. 2023Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Modelscited by 359
  12. 2023Training-Free Layout Control with Cross-Attention Guidancecited by 313
  13. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 308
  14. 2023Photorealistic Video Generation with Diffusion Modelscited by 306
  15. 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305
  16. 2023BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusioncited by 282
  17. 2023HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Modelscited by 225
  18. 2023Subject-driven Text-to-Image Generation via Apprenticeship Learningcited by 212
  19. 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localizationcited by 187
  20. 2024EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domaincited by 184
  21. 2023SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagerycited by 151
  22. 2023Foundation Models for Generalist Geospatial Artificial Intelligencecited by 149
  23. 2023DiffusionSat: A Generative Foundation Model for Satellite Imagerycited by 131
  24. 2023Lightweight, Pre-trained Transformers for Remote Sensing Timeseriescited by 103
  25. 2024Mission Critical -- Satellite Data is a Distinct Modality in Machine Learningcited by 77
  26. 2023Freestyle Layout-to-Image Synthesiscited by 67
  27. 2023EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-Resolutioncited by 56
  28. 2022DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylizationcited by 45
  29. 2022Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networkscited by 30
  30. 2024Large Language Models for Captioning and Retrieving Remote Sensing Imagescited by 30
  31. 2023SpectralDiff: A Generative Framework for Hyperspectral Image Classification with Diffusion Modelscited by 28
  32. 2021Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesiscited by 20
  33. 2023Sat2Cap: Mapping Fine-Grained Textual Descriptions from Satellite Imagescited by 19
  34. 2024Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignmentcited by 15
  35. 2023Learning Tri-modal Embeddings for Zero-Shot Soundscape Mappingcited by 14
  36. 2023Domain Expansion of Image Generatorscited by 13
  37. 2023Personalized Face Inpainting with Diffusion Models by Parallel Visual Attentioncited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 10; 2026: 20.

32 papers.

Sort:

By area:

  1. 2025Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectivescited by 18
  2. 2025EarthSynth: Generating Informative Earth Observation with Diffusion Modelscited by 12
  3. 2025Measuring the Intrinsic Dimension of Earth Representationscited by 10
  4. 2024Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidancecited by 9
  5. 2024CC-Diff: Enhancing Contextual Coherence in Remote Sensing Image Synthesiscited by 8
  6. 2025MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Datacited by 7
  7. 2025A Diffusion-Based Framework for Terrain-Aware Remote Sensing Image Reconstructioncited by 6
  8. 2025VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semanticscited by 5
  9. 2025MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUscited by 3
  10. 2025Can Location Embeddings Enhance Super-Resolution of Satellite Imagery?cited by 2
  11. 2025RSFAKE-1M: A Large-Scale Dataset for Detecting Diffusion-Generated Remote Sensing Forgeriescited by 2
  12. 2025TAMMs: Change Understanding and Forecasting in Satellite Image Time Series with Temporal-Aware Multimodal Modelscited by 2
20 more
  1. 2026RSEdit: Text-Guided Image Editing for Remote Sensingcited by 2
  2. 2026Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Datacited by 2
  3. 2026HuiYanEarth-SAR: A Foundation Model for High-Fidelity and Low-Cost Global Remote Sensing Imagery Generationcited by 2
  4. 2026Tessellating The Earthcited by 2
  5. 2026TerraDiT-Omega: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitivecited by 2
  6. 2026SimLBR: Learning to Detect Fake Images by Learning to Detect Real Imagescited by 1
  7. 2026A Proxy Consistency Loss for Grounded Fusion of Earth Observation and Location Encoderscited by 1
  8. 2026AnyBand-Diff: A Unified Remote Sensing Image Generation and Band Repair Framework with Spectral Priorscited by 1
  9. 2026MetaEarth-MM: Unified Multimodal Remote Sensing Image Generation with Scene-centered Joint Modelingcited by 1
  10. 2026TerraDiT: Point-Conditioned Diffusion Transformer for Satellite Image Synthesiscited by 0
  11. 2026Generating Satellite Imagery Data for Wildfire Detection through Mask-Conditioned Generative AIcited by 0
  12. 2026HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Compositioncited by 0
  13. 2026Efficient Geometry-Controlled High-Resolution Satellite Image Synthesiscited by 0
  14. 2026Earth Science Foundation Models: From Perception to Reasoning and Discoverycited by 0
  15. 2026D2-CDIG: Controlled Diffusion Remote Sensing Image Generation with Dual Priors of DEM and Cloud-Fogcited by 0
  16. 2026CAFOSat: A Strongly Annotated Dataset for Infrastructure-Aware CAFO Mapping Using High-Resolution Imagerycited by 0
  17. 2026Beyond Edge Maps: Wavelet-Domain Conditioning for Multi-Adapter Map-to-Satellite Diffusioncited by 0
  18. 2026Genesis: A Generative Engine for Hierarchical Satellite Image Synthesiscited by 0
  19. 2026Chronosphere: Space-Time Tessellation of Local Climate Expertscited by 0
  20. 2026From Pixels to Policy: A Multi-Agent System for Intervention and Geo-Spatial Decision Supportcited by 0