Coming Down To Earth: Satellite-to-street View Synthesis For Geo-localization
2021 · Aysim Toker, Qunjie Zhou, Maxim Maximov, et al.
Abstract
The goal of cross-view image based geo-localization is to determine the location of a given street view image by matching it against a collection of geo-tagged satellite images. This task is notoriously challenging due to the drastic viewpoint and appearance differences between the two domains. We show that we can address this discrepancy explicitly by learning to synthesize realistic street views from satellite inputs. Following this observation, we propose a novel multi-task architecture in which image synthesis and retrieval are considered jointly. The rationale behind this is that we can bias our network to learn latent feature representations that are useful for retrieval if we utilize them to generate images across the two input domains. To the best of our knowledge, ours is the first approach that creates realistic street views from satellite images and localizes the corresponding query street-view simultaneously in an end-to-end manner. In our experiments, we obtain state-of-th
Authors
(none)
Tags
Stats
Related papers
- Geo-localization Via Ground-to-satellite Cross-view Image Retrieval (2022)12.54
- Cross-view Image Matching For Geo-localization In Urban Environments (2017)17.16
- Skylink: Unifying Street-satellite Geo-localization Via Uav-mediated 3D Scene Alignment (2025)2.80
- Cross-view Localization And Synthesis -- Datasets, Challenges And Opportunities (2025)2.51
- From Street To Orbit: Training-free Cross-view Retrieval Via Location Semantics And LLM Guidance (2025)0.00
- VIGOR: Cross-view Image Geo-localization Beyond One-to-one Retrieval (2020)21.49
- Accurate 3-dof Camera Geo-localization Via Ground-to-satellite Image Matching (2022)12.17
- Localizing And Orienting Street Views Using Overhead Imagery (2016)17.26