# Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs

arXiv: https://arxiv.org/abs/2303.14672 · HTML: https://mlsanity.com/paper/2303.14672/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 26 Mar 2023.

## Builds on (most cited first, 27 of 27)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval](https://mlsanity.com/paper/2011.12172/) (2020)
- [SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image](https://mlsanity.com/paper/2204.00928/) (2022)
- [GAUDI: A Neural Architect for Immersive 3D Scene Generation](https://mlsanity.com/paper/2207.13751/) (2022)
- [Unconstrained Scene Generation with Locally Conditioned Radiance Fields](https://mlsanity.com/paper/2104.00670/) (2021)
- [GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds](https://mlsanity.com/paper/2104.07659/) (2021)
- [Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation](https://mlsanity.com/paper/1904.06807/) (2019)
- [Bridging the Domain Gap for Ground-to-Aerial Image Matching](https://mlsanity.com/paper/1904.11045/) (2019)
- [Optimal Feature Transport for Cross-View Image Geo-Localization](https://mlsanity.com/paper/1907.05021/) (2019)
- [Predicting Ground-Level Scene Layout from Aerial Imagery](https://mlsanity.com/paper/1612.02709/) (2016)
- [Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation](https://mlsanity.com/paper/2203.01452/) (2022)
- [Cross-View Image Synthesis using Conditional GANs](https://mlsanity.com/paper/1803.03396/) (2018)
- [Behind the Scenes: Density Fields for Single View Reconstruction](https://mlsanity.com/paper/2301.07668/) (2023)
- [Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery](https://mlsanity.com/paper/2103.01623/) (2021)
- [Cross-view image synthesis using geometry-guided conditional GANs](https://mlsanity.com/paper/1808.05469/) (2018)
- [Sat2Vid: Street-view Panoramic Video Synthesis from a Single Satellite Image](https://mlsanity.com/paper/2012.06628/) (2020)
- [Revisiting Near/Remote Sensing with Geospatial Attention](https://mlsanity.com/paper/2204.01807/) (2022)
- [Augmenting Depth Estimation with Geospatial Context](https://mlsanity.com/paper/2109.09879/) (2021)

## Built on by (most cited first, 29 of 29)

- [Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization](https://mlsanity.com/paper/2403.14198/) (2024)
- [Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion](https://mlsanity.com/paper/2401.10786/) (2024)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis](https://mlsanity.com/paper/2408.14765/) (2024)
- [Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery](https://mlsanity.com/paper/2510.15869/) (2025)
- [Multi-Level Embedding and Alignment Network with Consistency and Invariance Learning for Cross-View Geo-Localization](https://mlsanity.com/paper/2412.14819/) (2024)
- [Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion](https://mlsanity.com/paper/2507.04403/) (2025)
- [Geospecific View Generation -- Geometry-Context Aware High-resolution Ground View Inference from Satellite Views](https://mlsanity.com/paper/2407.08061/) (2024)
- [Leveraging BEV Paradigm for Ground-to-Aerial Image Synthesis](https://mlsanity.com/paper/2408.01812/) (2024)
- [Seeing through Satellite Images at Street Views](https://mlsanity.com/paper/2505.17001/) (2025)
- [Sat2RealCity: Geometry-Aware and Appearance-Controllable 3D Urban Generation from Satellite Imagery](https://mlsanity.com/paper/2511.11470/) (2025)
- [Skyeyes: Ground Roaming using Aerial View Images](https://mlsanity.com/paper/2409.16685/) (2024)
- [Geometry-guided Cross-view Diffusion for One-to-many Cross-view Image Synthesis](https://mlsanity.com/paper/2412.03315/) (2024)
- [Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image](https://mlsanity.com/paper/2605.14984/) (2026)
- [Mixed-View Panorama Synthesis using Geospatially Guided Diffusion](https://mlsanity.com/paper/2407.09672/) (2024)
- [Satellite to GroundScape -- Large-scale Consistent Ground View Generation from Satellite Views](https://mlsanity.com/paper/2504.15786/) (2025)
- [Enhancing Monocular Height Estimation from Aerial Images with Street-view Images](https://mlsanity.com/paper/2311.02121/) (2023)
- [Geo2: Geometry-Guided Cross-view Geo-Localization and Image Synthesis](https://mlsanity.com/paper/2603.25819/) (2026)
- [Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image](https://mlsanity.com/paper/2606.24138/) (2026)
- [ABot-Earth 0.5: Generative 3D Earth Model](https://mlsanity.com/paper/2606.09967/) (2026)
- [GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation](https://mlsanity.com/paper/2608.17988/) (2026)
- [AerialGo: Walking-through City View Generation from Aerial Perspectives](https://mlsanity.com/paper/2412.00157/) (2024)
- [EO-VGGT: Orbital Ray-Conditioned 3D Foundation Models for Satellite Multi-View Reconstruction](https://mlsanity.com/paper/2607.00417/) (2026)
- [SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery](https://mlsanity.com/paper/2506.00600/) (2025)
- [Top2Pano: Learning to Generate Indoor Panoramas from Top-Down View](https://mlsanity.com/paper/2507.21371/) (2025)
- [From Satellite to Street: A Hybrid Framework Integrating Stable Diffusion and PanoGAN for Consistent Cross-View Synthesis](https://mlsanity.com/paper/2509.24369/) (2025)
- [Top2Ground: A Height-Aware Dual Conditioning Diffusion Model for Robust Aerial-to-Ground View Generation](https://mlsanity.com/paper/2511.08258/) (2025)
- [Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images](https://mlsanity.com/paper/2605.19656/) (2026)
- [CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation](https://mlsanity.com/paper/2609.36616/) (2026)

## 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.