# Cross-view image synthesis using geometry-guided conditional GANs

arXiv: https://arxiv.org/abs/1808.05469 · HTML: https://mlsanity.com/paper/1808.05469/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2018.

## Built on by (most cited first, 30 of 30)

- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization](https://mlsanity.com/paper/2103.06818/) (2021)
- [Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer](https://mlsanity.com/paper/2307.08015/) (2023)
- [Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery](https://mlsanity.com/paper/2103.01623/) (2021)
- [Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos](https://mlsanity.com/paper/2403.06351/) (2024)
- [Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs](https://mlsanity.com/paper/2303.14672/) (2023)
- [ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives](https://mlsanity.com/paper/2411.19083/) (2024)
- [GAMa: Cross-view Video Geo-localization](https://mlsanity.com/paper/2207.02431/) (2022)
- [Cross-View Exocentric to Egocentric Video Synthesis](https://mlsanity.com/paper/2107.03120/) (2021)
- [Cross-view geo-localization: a survey](https://mlsanity.com/paper/2406.09722/) (2024)
- [Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes](https://mlsanity.com/paper/2106.10876/) (2021)
- [Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization](https://mlsanity.com/paper/2202.01821/) (2022)
- [Leveraging BEV Paradigm for Ground-to-Aerial Image Synthesis](https://mlsanity.com/paper/2408.01812/) (2024)
- [CityGuessr: City-Level Video Geo-Localization on a Global Scale](https://mlsanity.com/paper/2411.06344/) (2024)
- [Seeing through Satellite Images at Street Views](https://mlsanity.com/paper/2505.17001/) (2025)
- [Local and Global GANs with Semantic-Aware Upsampling for Image Generation](https://mlsanity.com/paper/2203.00047/) (2022)
- [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)
- [Aerial Diffusion: Text Guided Ground-to-Aerial View Translation from a Single Image using Diffusion Models](https://mlsanity.com/paper/2303.11444/) (2023)
- [Mixed-View Panorama Synthesis using Geospatially Guided Diffusion](https://mlsanity.com/paper/2407.09672/) (2024)
- [Human Silhouette and Skeleton Video Synthesis through Wi-Fi signals](https://mlsanity.com/paper/2203.05864/) (2022)
- [From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generation](https://mlsanity.com/paper/2509.05469/) (2025)
- [DOMR: Establishing Cross-View Segmentation via Dense Object Matching](https://mlsanity.com/paper/2508.04050/) (2025)
- [Semantic-aware Network for Aerial-to-Ground Image Synthesis](https://mlsanity.com/paper/2308.06945/) (2023)
- [HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View](https://mlsanity.com/paper/2311.15478/) (2023)
- [VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale](https://mlsanity.com/paper/2604.12159/) (2026)
- [Survey on Controlable Image Synthesis with Deep Learning](https://mlsanity.com/paper/2307.10275/) (2023)
- [STRMs: Spatial Temporal Reasoning Models for Vision-Based Localization Rivaling GPS Precision](https://mlsanity.com/paper/2503.07939/) (2025)
- [Cross-view Localization and Synthesis -- Datasets, Challenges and Opportunities](https://mlsanity.com/paper/2510.22736/) (2025)
- [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)

We address the problem of generating images across two drastically different views, namely ground (street) and aerial (overhead) views. Image synthesis by itself is a very challenging computer vision task and is even more so when generation is conditioned on an image in another view. Due the difference in viewpoints, there is small overlapping field of view and little common content between these two views. Here, we try to preserve the pixel information between the views so that the generated image is a realistic representation of cross view input image. For this, we propose to use homography as a guide to map the images between the views based on the common field of view to preserve the details in the input image. We then use generative adversarial networks to inpaint the missing regions in the transformed image and add realism to it. Our exhaustive evaluation and model comparison demonstrate that utilizing geometry constraints adds fine details to the generated images and can be a better approach for cross view image synthesis than purely pixel based synthesis methods.