mlsanityData to 7 Oct 2026

Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis

arXiv 2106.11485 ↗First posted 22 Jun 2021cs.CV cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

High-resolution satellite imagery has proven useful for a broad range of tasks, including measurement of global human population, local economic livelihoods, and biodiversity, among many others. Unfortunately, high-resolution imagery is both infrequently collected and expensive to purchase, making it hard to efficiently and effectively scale these downstream tasks over both time and space. We propose a new conditional pixel synthesis model that uses abundant, low-cost, low-resolution imagery to generate accurate high-resolution imagery at locations and times in which it is unavailable. We show that our model attains photo-realistic sample quality and outperforms competing baselines on a key downstream task -- object counting -- particularly in geographic locations where conditions on the ground are changing rapidly.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 29 of its 54 references that are in the map. First posted on arXiv 22 Jun 2021.

Builds on

29 of 54 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  7. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  8. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  9. 2016Colorful Image Colorizationcited by 1,113
  10. 2017Deep Image Priorcited by 1,097
  11. 2018Self-Attention Generative Adversarial Networkscited by 809
  12. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
17 more
  1. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  2. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  3. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  4. 2017Functional Map of the Worldcited by 338
  5. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  6. 2018Deep Back-Projection Networks For Super-Resolutioncited by 224
  7. 2019EdgeConnect: Generative Image Inpainting with Adversarial Edge Learningcited by 161
  8. 2019xBD: A Dataset for Assessing Building Damage from Satellite Imagerycited by 138
  9. 2019Image Super-Resolution by Neural Texture Transfercited by 119
  10. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 105
  11. 2020Using satellite imagery to understand and promote sustainable developmentcited by 71
  12. 2018The Effects of Super-Resolution on Object Detection Performance in Satellite Imagerycited by 57
  13. 2020Generating Interpretable Poverty Maps using Object Detection in Satellite Imagescited by 27
  14. 2020Comparison of Image Quality Models for Optimization of Image Processing Systemscited by 7
  15. 2017TensorLayer: A Versatile Library for Efficient Deep Learning Developmentcited by 6
  16. 2020Predicting Landsat Reflectance with Deep Generative Fusioncited by 2
  17. 2020Single Image Super-resolution with a Switch Guided Hybrid Network for Satellite Imagescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 9; 2024: 3; 2025: 3; 2026: 2.

20 papers.

Sort:

By area:

  1. 2022SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagerycited by 402
  2. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 302
  3. 2023DiffusionSat: A Generative Foundation Model for Satellite Imagerycited by 130
  4. 2023On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligencecited by 88
  5. 2023CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representationscited by 67
  6. 2023Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictionscited by 38
  7. 2024GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesiscited by 32
  8. 2024Large Language Models for Manufacturingcited by 24
  9. 2023Multimodality of AI for Education: Towards Artificial General Intelligencecited by 21
  10. 2023Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challengescited by 14
  11. 2024S4: Self-Supervised Sensing Across the Spectrumcited by 5
  12. 2025VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semanticscited by 5
8 more
  1. 2023Zooming Out on Zooming In: Advancing Super-Resolution for Remote Sensingcited by 3
  2. 2022Tracking Urbanization in Developing Regions with Remote Sensing Spatial-Temporal Super-Resolutioncited by 2
  3. 2023SSIF: Learning Continuous Image Representation for Spatial-Spectral Super-Resolutioncited by 2
  4. 2023TSGAN: An Optical-to-SAR Dual Conditional GAN for Optical based SAR Temporal Shiftingcited by 2
  5. 2026TerraDiT-Omega: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitivecited by 2
  6. 2025Resolution Revolution: A Physics-Guided Deep Learning Framework for Spatiotemporal Temperature Reconstructioncited by 1
  7. 2026Beyond Visual Fidelity: Benchmarking Super-Resolution Models for Large-Scale Remote Sensing Imagery via Downstream Task Integrationcited by 1
  8. 2025Controllable Reference Guided Diffusion with Local Global Fusion for Real World Remote Sensing Image Super Resolutioncited by 0