DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Persistent Learning for Semantic Indoor Mapping in Dynamic Environments

Denninger, Maximilian (2023) Persistent Learning for Semantic Indoor Mapping in Dynamic Environments. Dissertation, Technische Universität München.

[img] PDF

Official URL: https://mediatum.ub.tum.de/?id=1703886


Leveraging deep learning, we propose in this work an approach to tackle the problem of 3D scene reconstruction from single color images in indoor spaces. We rely here on synthetic data and show how to tackle the hard problem of sim2real transfer. Besides a 3D scene reconstruction, we further provide a semantic segmentation of the current viewport.

Item URL in elib:https://elib.dlr.de/202781/
Document Type:Thesis (Dissertation)
Title:Persistent Learning for Semantic Indoor Mapping in Dynamic Environments
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Denninger, MaximilianUNSPECIFIEDhttps://orcid.org/0000-0002-1557-2234UNSPECIFIED
Open Access:Yes
Number of Pages:177
Keywords:3d modeling; 3d scene representation; deep learning; simulation
Institution:Technische Universität München
Department:TUM School of Computation, Information and Technology
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Robotics
DLR - Research area:Raumfahrt
DLR - Program:R RO - Robotics
DLR - Research theme (Project):R - Multisensory World Modelling (RM) [RO]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Institute of Robotics and Mechatronics (since 2013)
Deposited By: Strobl, Dr. Klaus H.
Deposited On:14 Feb 2024 08:13
Last Modified:14 Feb 2024 08:13

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.