Benutzer: Gast  Login
Titel:

THE Benchmark: Transferable Representation Learning for Monocular Height Estimation

Dokumenttyp:
Forschungsdaten
Veröffentlichungsdatum:
30.06.2022
Verantwortlich:
Zhu, Xiao Xiang
Autorinnen / Autoren:
Xiong, Zhitong; Huang, Wei; Hu, Jingtao; Shi, Yilei; Wang, Qi; Zhu, Xiao Xiang
Institutionszugehörigkeit:
TUM
Herausgeber:
TUM
Identifikator:
doi:10.14459/2022mp1662763.001
Konzept-DOI:
doi:10.14459/2022mp1662763
Enddatum der Datenerzeugung:
15.12.2021
Fachgebiet:
DAT Datenverarbeitung, Informatik; GEO Geowissenschaften
Quellen der Daten:
Abbildungen von Objekten / image of objects
Datentyp:
Bilder / images
Methode der Datenerhebung:
Automatic download, image preparation and processing using Python
Beschreibung:
Generating 3D city models rapidly is crucial for many applications. Monocular height estimation is one of the most efficient and timely ways to obtain large-scale geometric information. However, existing works focus primarily on training and testing models using unbiased datasets, which don’t align well with real-world applications. Therefore, we propose a new benchmark dataset to study the transferability of height estimation models in a cross-dataset setting. To this end, we first design and c...     »
Links:

THE Benchmark on GitHub: https://thebenchmarkh.github.io/

Schlagworte:
Cross-dataset Transfer; Remote Sensing; Synthetic Data; Transfer Learning; Transformer; Benchmark
Technische Hinweise:
View and download (26 GB total, 2 Files)
The data server also offers downloads with FTP
The data server also offers downloads with rsync (password m1662763):
rsync rsync://m1662763.001@dataserv.ub.tum.de/m1662763.001/
Sprache:
en
Rechte:
by, http://creativecommons.org/licenses/by/4.0
 BibTeX