mlsanityData to 7 Oct 2026

GPS as a Control Signal for Image Generation

arXiv 2501.12390 ↗First posted 21 Jan 2025cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

We show that the GPS tags contained in photo metadata provide a useful control signal for image generation. We train GPS-to-image models and use them for tasks that require a fine-grained understanding of how images vary within a city. In particular, we train a diffusion model to generate images conditioned on both GPS and text. The learned model generates images that capture the distinctive appearance of different neighborhoods, parks, and landmarks. We also extract 3D models from 2D GPS-to-image models through score distillation sampling, using GPS conditioning to constrain the appearance of the reconstruction from each viewpoint. Our evaluations suggest that our GPS-conditioned models successfully learn to generate images that vary based on location, and that GPS conditioning improves estimated 3D structure.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 79 of its 109 references that are in the map. First posted on arXiv 21 Jan 2025.

Builds on

79 of 109 references.

References · 79

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  9. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  10. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  11. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  12. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
38 more
  1. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  2. 2022Scalable Diffusion Models with Transformerscited by 5,931
  3. 2022Classifier-Free Diffusion Guidancecited by 5,717
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  8. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  9. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  10. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  11. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  12. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  13. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  14. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  15. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  16. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  17. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  18. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  19. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  20. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  21. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  22. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  23. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 568
  24. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 568
  25. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 529
  26. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  27. 2024Evaluating Text-to-Visual Generation with Image-to-Text Generationcited by 465
  28. 2017Functional Map of the Worldcited by 338
  29. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingcited by 293
  30. 2023DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectorycited by 260
  31. 2021CLIP-Forge: Towards Zero-Shot Text-to-Shape Generationcited by 254
  32. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  33. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  34. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCcited by 216
  35. 2023Any-to-Any Generation via Composable Diffusioncited by 203
  36. 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localizationcited by 185
  37. 20234D-fy: Text-to-4D Generation Using Hybrid Score Distillation Samplingcited by 184
  38. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156

50 most cited of 79 All 79 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Measuring the Intrinsic Dimension of Earth Representationscited by 10
  2. 2026DiffPlace: Street View Generation via Place-Controllable Diffusion Model Enhancing Place Recognitioncited by 1
  3. 2026Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignmentcited by 1
  4. 2026GeoFidelity-Bench: Evaluating Block-Conditioned Geographic Fidelity in Text-to-Image Street-View Generationcited by 0
  5. 2026On the Diffusibility of High-Dimensional Latentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion
  2. 2025DiffVL: Diffusion-Based Visual Localization on 2D Maps via BEV-Conditioned GPS Denoising
  3. 2025Environment-Aware Satellite Image Generation with Diffusion Models
  4. 2025Generative AI in Map-Making: A Technical Exploration and Its Implications for Cartographers
  5. 2023GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation
  6. 2025Generative AI for Urban Planning: Synthesizing Satellite Imagery via Diffusion Models
  7. 2024PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models
  8. 2023Training-Free Location-Aware Text-to-Image Synthesis