mlsanityData to 7 Oct 2026

Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs

arXiv 2303.14672 ↗First posted 26 Mar 2023cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

This paper aims to develop an accurate 3D geometry representation of satellite images using satellite-ground image pairs. Our focus is on the challenging problem of 3D-aware ground-views synthesis from a satellite image. We draw inspiration from the density field representation used in volumetric neural rendering and propose a new approach, called Sat2Density. Our method utilizes the properties of ground-view panoramas for the sky and non-sky regions to learn faithful density fields of 3D scenes in a geometric perspective. Unlike other methods that require extra depth information during training, our Sat2Density can automatically learn accurate and faithful 3D geometry via density representation without depth supervision. This advancement significantly improves the ground-view panorama synthesis task. Additionally, our study provides a new geometric perspective to understand the relationship between satellite and ground-view images in 3D space.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 27 of its 39 references that are in the map. First posted on arXiv 26 Mar 2023.

Builds on

27 of 39 references.

References · 27

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  4. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  5. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  7. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  8. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  9. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  10. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  11. 2020VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrievalcited by 188
  12. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
15 more
  1. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  2. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  3. 2021GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worldscited by 98
  4. 2019Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translationcited by 97
  5. 2019Bridging the Domain Gap for Ground-to-Aerial Image Matchingcited by 95
  6. 2019Optimal Feature Transport for Cross-View Image Geo-Localizationcited by 90
  7. 2016Predicting Ground-Level Scene Layout from Aerial Imagerycited by 89
  8. 2022Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentationcited by 71
  9. 2018Cross-View Image Synthesis using Conditional GANscited by 69
  10. 2023Behind the Scenes: Density Fields for Single View Reconstructioncited by 63
  11. 2021Geometry-Guided Street-View Panorama Synthesis from Satellite Imagerycited by 41
  12. 2018Cross-view image synthesis using geometry-guided conditional GANscited by 30
  13. 2020Sat2Vid: Street-view Panoramic Video Synthesis from a Single Satellite Imagecited by 25
  14. 2022Revisiting Near/Remote Sensing with Geospatial Attentioncited by 12
  15. 2021Augmenting Depth Estimation with Geospatial Contextcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 10; 2025: 10; 2026: 8.

29 papers.

Sort:

By area:

  1. 2024Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localizationcited by 31
  2. 2024Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusioncited by 27
  3. 20253D Scene Generation: A Surveycited by 24
  4. 2024CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesiscited by 23
  5. 2024Multi-Level Embedding and Alignment Network with Consistency and Invariance Learning for Cross-View Geo-Localizationcited by 16
  6. 2025Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagerycited by 16
  7. 2025Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusioncited by 15
  8. 2024Geospecific View Generation -- Geometry-Context Aware High-resolution Ground View Inference from Satellite Viewscited by 13
  9. 2024Leveraging BEV Paradigm for Ground-to-Aerial Image Synthesiscited by 11
  10. 2025Seeing through Satellite Images at Street Viewscited by 8
  11. 2025Sat2RealCity: Geometry-Aware and Appearance-Controllable 3D Urban Generation from Satellite Imagerycited by 6
  12. 2024Skyeyes: Ground Roaming using Aerial View Imagescited by 5
17 more
  1. 2024Geometry-guided Cross-view Diffusion for One-to-many Cross-view Image Synthesiscited by 5
  2. 2024Mixed-View Panorama Synthesis using Geospatially Guided Diffusioncited by 4
  3. 2025Satellite to GroundScape -- Large-scale Consistent Ground View Generation from Satellite Viewscited by 4
  4. 2026Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Imagecited by 4
  5. 2023Enhancing Monocular Height Estimation from Aerial Images with Street-view Imagescited by 3
  6. 2026Geo2: Geometry-Guided Cross-view Geo-Localization and Image Synthesiscited by 3
  7. 2026ABot-Earth 0.5: Generative 3D Earth Modelcited by 2
  8. 2026Sat2City v2: Native 3D City Asset Generation from a Single Satellite Imagecited by 2
  9. 2024AerialGo: Walking-through City View Generation from Aerial Perspectivescited by 1
  10. 2026EO-VGGT: Orbital Ray-Conditioned 3D Foundation Models for Satellite Multi-View Reconstructioncited by 1
  11. 2026GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generationcited by 1
  12. 2025SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagerycited by 0
  13. 2025Top2Pano: Learning to Generate Indoor Panoramas from Top-Down Viewcited by 0
  14. 2025From Satellite to Street: A Hybrid Framework Integrating Stable Diffusion and PanoGAN for Consistent Cross-View Synthesiscited by 0
  15. 2025Top2Ground: A Height-Aware Dual Conditioning Diffusion Model for Robust Aerial-to-Ground View Generationcited by 0
  16. 2026Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Imagescited by 0
  17. 2026CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generationcited by 0