Tell a friend
Print
Denninger, Maximilian (2023) Persistent Learning for Semantic Indoor Mapping in Dynamic Environments. Dissertation, Technische Universität München.
![[img]](https://elib.dlr.de/style/images/fileicons/application_pdf.png) |
PDF
31MB |
Official URL: https://mediatum.ub.tum.de/?id=1703886
Abstract
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 | ||||||||
| Authors: |
| ||||||||
| Date: | 2023 | ||||||||
| Open Access: | Yes | ||||||||
| Number of Pages: | 177 | ||||||||
| Status: | Published | ||||||||
| 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
