Accurate Geo-Registration by Ground-to-Aerial Image Matching

We address the problem of geo-registering ground-based multi-view stereo models by ground-to-aerial image matching. The main contribution is a fully automated geo-registration pipeline with a novel viewpoint-dependent matching method that handles ground to aerial viewpoint variation. We conduct large-scale experiments which consist of many popular outdoor landmarks in Rome. The proposed approach demonstrates a high success rate for the task, and dramatically outperforms state-of-the-art techniques, yielding geo-registration at pixel-level accuracy.

• Publication year

  2014

• Venue

  International Conference on 3D Vision

• Publication date

  2014-12-01

• Fields of study

  Geography, Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/3DV.2014.69
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Image Geo-Localization Based on MultipleNearest Neighbor Feature Matching UsingGeneralized Graphs

  2014cited by this paper
• Occluding Contours for Multi-view Stereo

  2014cited by this paper
• Towards Linear-Time Incremental Structure from Motion

  2013cited by this paper
• Accurate Georegistration of Point Clouds Using Geographic Data

  2013cited by this paper
• The Visual Turing Test for Scene Reconstruction

  2013cited by this paper
• Geo-registered 3D models from crowdsourced image collections

  2013cited by this paper
• Ultra-wide Baseline Facade Matching for Geo-localization

  2012cited by this paper
• Worldwide Pose Estimation Using 3D Point Clouds

  2012cited by this paper
• Photo Tours

  2012cited by this paper
• PhotoCity: training experts at large-scale image acquisition through a competitive game

  2011cited by this paper
• Guided Image Filtering

  2010cited by this paper
• Building Rome on a Cloudless Day

  2010cited by this paper
• Avoiding Confusing Features in Place Recognition

  2010cited by this paper
• 3D exploitation of large urban photo archives

  2010cited by this paper
• From structure-from-motion point clouds to fast location recognition

  2009cited by this paper
• Alignment of 3D point clouds to overhead images

  2009cited by this paper
• ASIFT: A New Framework for Fully Affine Invariant Image Comparison

  2009influential reference
• Building Rome in a day

  2009cited by this paper
• Fast Point Feature Histograms (FPFH) for 3D registration

  2009cited by this paper
• 3D model matching with Viewpoint-Invariant Patches (VIP)

  2008cited by this paper
• 3D model search and pose estimation from single images using VIP features

  2008cited by this paper
• IM2GPS: estimating geographic information from a single image

  2008cited by this paper
• Accurate, Dense, and Robust Multi-View Stereopsis

  2007cited by this paper
• Photo Tourism : Exploring image collections in 3D

  2006cited by this paper
• Distinctive Image Features from Scale-Invariant Keypoints

  2004influential reference
• Constructing 3D city models by merging ground-based and airborne views

  2003cited by this paper
• A Method for Registration of 3-D Shapes

  1992cited by this paper
• Least-Squares Estimation of Transformation Parameters Between Two Point Patterns

  1991cited by this paper
• Author manuscript, published in "International Conference on Computer Vision and Pattern Recognition (2009)" Surface Feature Detection and Description with Applications to Mesh Matching

  year unknowncited by this paper

• Wrivinder: Towards Spatial Intelligence for Geo-locating Ground Images onto Satellite Imagery

  2026cites this paper
• Frequency-Enhanced Network for cross-view geolocalization

  2025cites this paper
• Cross-view geolocation via segmentation and common region feature matching

  2025cites this paper
• Metadata-free Georegistration of Ground and Airborne Imagery

  2025cites this paper
• Aerial-Ground Image Feature Matching via 3D Gaussian Splatting-based Intermediate View Rendering

  2025cites this paper
• AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis

  2025cites this paper
• Cross-View Open-Vocabulary Object Detection in Aerial Imagery

  2025cites this paper
• Crafting Challenges for Varying-Altitude Novel View Synthesis

  2025cites this paper
• Unconstrained Large-scale 3D Reconstruction and Rendering across Altitudes

  2025cites this paper
• Multiplatform Bundle Adjustment Method Supported by Object Structural Information

  2024cites this paper
• MeshVPR: Citywide Visual Place Recognition Using 3D Meshes

  2024cites this paper
• A Semantic Segmentation-Guided Approach for Ground-to-Aerial Image Matching

  2024cites this paper
• ATLoc: Aerial Thermal Images Localization via View Synthesis

  2024cites this paper
• The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement

  2024cites this paper
• SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs

  2024cites this paper
• UGVs’ Navigation Supported by Multi-UAVs in an ROS Environment

  2024cites this paper
• Penguin colony georegistration using camera pose estimation and phototourism

  2024cites this paper
• Registration of Aerial and Ground Images for 3D Reconstruction Using Tie Point Filtering Based on Reprojection Errors

  2024cites this paper
• Learning Dense Consistent Features for Aerial-to-Ground Structure-From-Motion

  2023cites this paper
• Linear target change detection from a single image based on three‐dimensional real scene

  2023cites this paper
• Multiview Aerial Visual Recognition (MAVREC): Can Multi-View Improve Aerial Visual Perception?

  2023cites this paper
• An Automated Ground-to-Aerial Viewpoint Localization for Content Verification

  2023cites this paper
• Visual Localization using Imperfect 3D Models from the Internet

  2023influential citation
• OoD-Pose: Camera Pose Regression From Out-of-Distribution Synthetic Views

  2022cites this paper
• A Down-to-Earth Approach for Camera to World Map Georeferencing Using SfM

  2022cites this paper
• MeshLoc: Mesh-Based Visual Localization

  2022influential citation
• Global alignment of HD maps and satellite imagery for Autonomous Navigation

  2022cites this paper
• A Graph-Matching Approach for Cross-view Registration of Over-view 2 and Street-view based Point Clouds

  2022cites this paper
• Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization

  2022cites this paper
• Geographic Semantic Network for Cross-View Image Geo-Localization

  2022cites this paper
• Lattice-Point Mutually Guided Ground-to-Aerial Feature Matching for Urban Scene Images

  2021cites this paper
• Ground and Aerial Collaborative Mapping in Urban Environments

  2021cites this paper
• Orthographic-Perspective Epipolar Geometry

  2021cites this paper
• Complete and Accurate Indoor Scene Capturing and Reconstruction Using a Drone and a Robot

  2021cites this paper
• Video Geo-Localization Employing Geo-Temporal Feature Learning and GPS Trajectory Smoothing

  2021cites this paper
• Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis

  2020cites this paper
• Leveraging Photogrammetric Mesh Models for Aerial-Ground Feature Point Matching Toward Integrated 3D Reconstruction

  2020cites this paper
• POSE ESTIMATION OF A MOVING CAMERA WITH LOW-COST, MULTI-GNSS DEVICES

  2020cites this paper
• Automatic Deep Inference of Procedural Cities from Global-scale Spatial Data

  2020cites this paper
• Evaluation of Cross-View Matching to Improve Ground Vehicle Localization with Aerial Perception

  2020cites this paper
• Cross-Time and Orientation-Invariant Overhead Image Geolocalization Using Deep Local Features

  2020cites this paper
• Continuous Indoor Visual Localization Using a Spatial Model and Constraint

  2020cites this paper
• Reference Pose Generation for Visual Localization via Learned Features and View Synthesis

  2020cites this paper
• Camera Re-Localization with Data Augmentation by Image Rendering and Image-to-Image Translation

  2020cites this paper
• Ground-to-Aerial Viewpoint Localization via Landmark Graphs Matching

  2020cites this paper
• Using UAV and LiDAR data for gully geomorphic changes monitoring

  2020cites this paper
• A Practical Cross-View Image Matching Method between UAV and Satellite for UAV-Based Geo-Localization

  2020cites this paper
• Feature Matching with Similarity Domains Network

  2020cites this paper
• Integrated georeferencing for precise depth map generation exploiting multi-camera image sequences from mobile mapping

  2020cites this paper
• Image-Based Monte-Carlo Localization With Information Allocation Logic to Mitigate Shadow Effect

  2020cites this paper
• View synthesis for pose computation

  2019influential citation
• Image-Based Geo-Localization Using Satellite Imagery

  2019cites this paper
• Towards accurate camera geopositioning by image matching

  2019cites this paper
• Tutorial: Dealing with rotation matrices and translation vectors in image-based applications: A common reference system for cameras

  2019cites this paper
• Tutorial: Dealing with rotation matrices and translation vectors in image-based applications: A tutorial

  2019cites this paper
• Improving Details of Building Façades in Open LiDAR Data Using Ground Images

  2019influential citation
• From Google Maps to a Fine-Grained Catalog of Street trees

  2019cites this paper
• Ground and aerial meta-data integration for localization and reconstruction: A review

  2019cites this paper
• Bridging the Domain Gap for Ground-to-Aerial Image Matching

  2019cites this paper
• Co‐registration of panoramic mobile mapping images and oblique aerial images

  2019cites this paper
• GEOCAPSNET: Ground to Aerial View Image Geo-Localization using Capsule Network

  2019cites this paper
• Is This the Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization

  2019cites this paper
• Beyond Cartesian Representations for Local Descriptors

  2019cites this paper
• Multi-source data-based 3D digital preservation of largescale ancient chinese architecture: A case report

  2019cites this paper
• IMAGE-TO-IMAGE TRANSLATION FOR ENHANCED FEATURE MATCHING, IMAGE RETRIEVAL AND VISUAL LOCALIZATION

  2019cites this paper
• Distorted Building Image Matching with Automatic Viewpoint Rectification and Fusion

  2019cites this paper
• Research On 3D Reconstruction of Face Based on Binocualr Stereo Vision

  2019cites this paper
• Siddiqi, Muftooh U. R. and Ijomah, Winifred L. and Dobie, Gordon I. and Hafeez, Muthair and Pierce, S. Gareth and Ion, William and Mineo, Carmelo and MacLeod, Charles N. (2018) Low cost three-dimensional virtual model construction for remanufacturing

  2019cites this paper
• Geolocation Estimation of Photos Using a Hierarchical Model and Scene Classification

  2018cites this paper
• AgriColMap: Aerial-Ground Collaborative 3D Mapping for Precision Farming

  2018cites this paper
• CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization

  2018cites this paper
• Scientific Cooperation and Implementation of New Technologies for the Development of Archaeological Heritage

  2018cites this paper
• Ancient Chinese architecture 3D preservation by merging ground and aerial point clouds

  2018cites this paper
• 3D Reconstruction of Urban Scenes from Street-Side and Airborne Imagery

  2018cites this paper
• Large-scale probabilistic aerial reconstruction

  2018cites this paper
• Augmented reality over video stream acquired from UAVs for operations support

  2018cites this paper
• Leveraging Overhead Imagery for Localization, Mapping, and Understanding

  2018cites this paper
• Accurate and efficient ground-to-aerial model alignment

  2018cites this paper
• Improve Building Façades in Open Lidar Data Using Ground Imagery

  2018cites this paper
• Aerial-DEM geolocalization for GPS-denied UAS navigation

  2018cites this paper
• Mini-UAV-based Remote Sensing: Techniques, Applications and Prospectives

  2018cites this paper
• 24/7 Place Recognition by View Synthesis

  2018cites this paper
• Registration of Heterogenous Data for Urban Modeling

  2018cites this paper
• Impact of Next-Generation Mobile Technologies on IoT-Cloud Convergence

  2017cites this paper
• Imaging-to-Simulation Framework for Improving Disaster Preparedness of Construction Projects and Neighboring Communities

  2017cites this paper
• Low cost three-dimensional virtual model construction for remanufacturing industry

  2017cites this paper
• Temporal city modeling using street level imagery

  2017cites this paper
• Synthèse de vues pour l'initialisation de pose. (Viewpoint synthesis for camera pose initialisation)

  2017cites this paper
• Accurate vehicle self-localization in high definition map dataset

  2017cites this paper
• A Method for Estimating Surveillance Video Georeferences

  2017cites this paper
• Automatic UAV Image Geo-Registration by Matching UAV Images to Georeferenced Image Data

  2017cites this paper
• The light field 3D scanner

  2017cites this paper
• Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art

  2017cites this paper
• Enabling Mobile and Wireless Technologies for Smart Cities

  2017cites this paper
• Revisiting IM2GPS in the Deep Learning Era

  2017cites this paper
• Cross-View Image Matching for Geo-Localization in Urban Environments

  2017cites this paper
• Progressive Large Scale-Invariant Image Matching in Scale Space

  2017cites this paper
• Automatic Registration of Images to Untextured Geometry Using Average Shading Gradients

  2017cites this paper
• Ground2sky label transfer for fine-grained aerial car recognition

  2017cites this paper
• Accurate mesh-based alignment for ground and aerial multi-view stereo models

  2017influential citation