3D Reconstruction through Fusion of Cross-View Images

TL;DR

This paper presents a novel framework for 3D reconstruction by fusing ground-view and satellite images, enabling detailed 3D models from drastically different viewpoints, with applications in remote sensing and computer vision.

Contribution

The authors introduce a comprehensive framework that combines satellite and ground images for full 3D recovery, including point cloud generation, co-registration, fusion, and mesh creation.

Findings

Successful 3D reconstruction from diverse viewpoints

Comparison shows improved results over traditional geo-registration methods

Framework applied to large datasets with high accuracy

Abstract

3D recovery from multi-stereo and stereo images, as an important application of the image-based perspective geometry, serves many applications in computer vision, remote sensing and Geomatics. In this chapter, the authors utilize the imaging geometry and present approaches that perform 3D reconstruction from cross-view images that are drastically different in their viewpoints. We introduce our framework that takes ground-view images and satellite images for full 3D recovery, which includes necessary methods in satellite and ground-based point cloud generation from images, 3D data co-registration, fusion and mesh generation. We demonstrate our proposed framework on a dataset consisting of twelve satellite images and 150k video frames acquired through a vehicle-mounted Go-pro camera and demonstrate the reconstruction results. We have also compared our results with results generated from an intuitive processing pipeline that involves typical geo-registration and meshing methods.