# Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance

arXiv: https://arxiv.org/abs/2408.04224 · HTML: https://mlsanity.com/paper/2408.04224/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 73 references that are in the map.
- First posted on arXiv 8 Aug 2024.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation](https://mlsanity.com/paper/1611.06612/) (2016)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://mlsanity.com/paper/2205.02833/) (2022)
- [Diffsound: Discrete Diffusion Model for Text-to-sound Generation](https://mlsanity.com/paper/2207.09983/) (2022)
- [MagicDrive: Street View Generation with Diverse 3D Geometry Control](https://mlsanity.com/paper/2310.02601/) (2023)
- [FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras](https://mlsanity.com/paper/2104.10490/) (2021)
- [VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval](https://mlsanity.com/paper/2011.12172/) (2020)
- [Wide-Area Image Geolocalization with Aerial Reference Imagery](https://mlsanity.com/paper/1510.03743/) (2015)
- [Lending Orientation to Neural Networks for Cross-view Geo-localization](https://mlsanity.com/paper/1903.12351/) (2019)
- [University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization](https://mlsanity.com/paper/2002.12186/) (2020)
- [Putting People in their Place: Monocular Regression of 3D People in Depth](https://mlsanity.com/paper/2112.08274/) (2021)
- [Translating Images into Maps](https://mlsanity.com/paper/2110.00966/) (2021)
- [Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization](https://mlsanity.com/paper/2103.06818/) (2021)
- [Person Image Synthesis via Denoising Diffusion Model](https://mlsanity.com/paper/2211.12500/) (2022)
- [PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval](https://mlsanity.com/paper/1706.03424/) (2017)
- [Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation](https://mlsanity.com/paper/1904.06807/) (2019)
- [Deep Visual Geo-localization Benchmark](https://mlsanity.com/paper/2204.03444/) (2022)

## Built on by (most cited first, 9 of 9)

- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives](https://mlsanity.com/paper/2505.14361/) (2025)
- [REOBench: Benchmarking Robustness of Earth Observation Foundation Models](https://mlsanity.com/paper/2505.16793/) (2025)
- [Unsupervised Multi-view UAV Image Geo-localization via Iterative Rendering](https://mlsanity.com/paper/2411.14816/) (2024)
- [From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generation](https://mlsanity.com/paper/2509.05469/) (2025)
- [Geo2: Geometry-Guided Cross-view Geo-Localization and Image Synthesis](https://mlsanity.com/paper/2603.25819/) (2026)
- [DiffusionUavLoc: Visually Prompted Diffusion for Cross-View UAV Localization](https://mlsanity.com/paper/2511.06422/) (2025)
- [Turning Generators into Retrievers: Unlocking MLLMs for Natural Language-Guided Geo-Localization](https://mlsanity.com/paper/2604.10721/) (2026)
- [TerraDiT: Point-Conditioned Diffusion Transformer for Satellite Image Synthesis](https://mlsanity.com/paper/2603.02172/) (2026)

## Abstract (arXiv)

Aerial imagery analysis is critical for many research fields. However, obtaining frequent high-quality aerial images is not always accessible due to its high effort and cost requirements. One solution is to use the Ground-to-Aerial (G2A) technique to synthesize aerial images from easily collectible ground images. However, G2A is rarely studied, because of its challenges, including but not limited to, the drastic view changes, occlusion, and range of visibility. In this paper, we present a novel Geometric Preserving Ground-to-Aerial (G2A) image synthesis (GPG2A) model that can generate realistic aerial images from ground images. GPG2A consists of two stages. The first stage predicts the Bird's Eye View (BEV) segmentation (referred to as the BEV layout map) from the ground image. The second stage synthesizes the aerial image from the predicted BEV layout map and text descriptions of the ground image. To train our model, we present a new multi-modal cross-view dataset, namely VIGORv2 which is built upon VIGOR with newly collected aerial images, maps, and text descriptions. Our extensive experiments illustrate that GPG2A synthesizes better geometry-preserved aerial images than existing models. We also present two applications, data augmentation for cross-view geo-localization and sketch-based region search, to further verify the effectiveness of our GPG2A. The code and data will be publicly available.