Benutzer: Gast  Login
Dokumenttyp:
Masterarbeit
Autor(en):
Fröch, Thomas
eMail-Adresse:
thomas.froech@tum.de
Titel:
Inpainting of unseen façade objects using deep learning methods
Übersetzter Titel:
Inpainting von unbeobachteten Gebäudefassadenobjekten mit Deep-Learning-Methoden
Abstract:
In the realm of 3D reconstruction pipelines, 2D conflict maps that indicate the presence openings in façades such as windows and doors, represent an intermediate output [1]. However, these maps often fall short of completeness due to insufficient coverage or occlusions caused by objects such as vegetation. This research delves into the exploration of deep learning strategies to address this limitation by inpainting unseen façade objects into the 2D conflict maps. The central focus of this study...     »
Stichworte:
GISTop_CitySystemModeling; GISTop_CityModeling; GISTop_SpatialModelingAndAlgorithms; LOCTop_Data_generation_and_object_reconstruction; LOCTop_Spatial_modeling_and_algorithms; LOCTop_Urban_Information_Modeling_Virtual_3D_City_Model
Aufgabensteller:
Kolbe, Thomas H
Betreuer:
Schwab, Benedikt; Wysocki, Olaf; Xia, Yan
Jahr:
2023
Quartal:
4. Quartal
Jahr / Monat:
2023-11
Monat:
Nov
Seiten/Umfang:
84
Sprache:
en
Hochschule / Universität:
Technical University of Munich
Fakultät:
TUM School of Engineering and Design
TUM Einrichtung:
Chair of Geoinformatics
Bearbeitungsbeginn:
31.05.2023
Bearbeitungsende:
30.11.2023
Präsentationsdatum:
07.12.2023
Status:
Abgeschlossen
 BibTeX