3D Reconstruction through Fusion of Cross-View Images
This work addresses 3D reconstruction for applications in computer vision, remote sensing, and Geomatics, but appears incremental as it builds on existing imaging geometry and methods.
The authors tackled 3D reconstruction from cross-view images with drastically different viewpoints, such as ground-view and satellite images, and demonstrated their framework on a dataset of twelve satellite images and 150k video frames, showing reconstruction results compared to a baseline pipeline.
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.