# 3D Reconstruction through Fusion of Cross-View Images

arXiv: https://arxiv.org/abs/2106.14306 · HTML: https://mlsanity.com/paper/2106.14306/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 58 references that are in the map.
- First posted on arXiv 27 Jun 2021.

## Builds on (most cited first, 5 of 5)

- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Cross-View Image Matching for Geo-localization in Urban Environments](https://mlsanity.com/paper/1703.07815/) (2017)
- [Cross-View Image Synthesis using Conditional GANs](https://mlsanity.com/paper/1803.03396/) (2018)
- [Semantic Cross-View Matching](https://mlsanity.com/paper/1511.00098/) (2015)
- [Automated 3D recovery from very high resolution multi-view satellite images](https://mlsanity.com/paper/1905.07475/) (2019)

## Built on by (most cited first, 2 of 2)

- [CrossView-GS: Cross-view Gaussian Splatting For Large-scale Scene Reconstruction](https://mlsanity.com/paper/2501.01695/) (2025)
- [Automated 3D-GS Registration and Fusion via Skeleton Alignment and Gaussian-Adaptive Features](https://mlsanity.com/paper/2507.20480/) (2025)

## Abstract (arXiv)

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.