3D Map Reconstruction From Single Satellite Image Using a Deep Monocular Depth Network

Citations

WEB OF SCIENCE

6
Citations

SCOPUS

6

초록

In this paper, we propose a 3D reconstruction scheme from single image with deep monocular depth estimation network, BTS (From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation) [1]. Furthermore, we expand it to height estimation focused building from remote sensing images. To address these issues, we substitute depth estimation loss function with height estimation loss function. Moreover, considering improving the quality of the building height map and looking as similar as possible to the ground-truth view, we apply building adaptive loss function.

키워드

3D map; Monocular height estimation; Deep learning; Remote sensing image
제목
3D Map Reconstruction From Single Satellite Image Using a Deep Monocular Depth Network
저자
Son, Changmin; Park, Soon-Yong
DOI
10.1109/ICUFN55119.2022.9829688
발행일
2022
유형
Proceedings Paper
저널명
2022 THIRTEENTH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS (ICUFN)
페이지
5 ~ 7