Login
- Original title:
- Robust Deformable 3D Shape Correspondence and Interpolation
- Translated title:
- Robuste Korrespondenz und Interpolation Deformierbarer 3D Formen
- Author:
- Eisenberger, Marvin Marc
- Year:
- 2024
- Document type:
- Dissertation
- Faculty/School:
- TUM School of Computation, Information and Technology
- Institution:
- Informatik 9 - Lehrstuhl für Computer Vision and Artificial Intelligence (Prof. Cremers)
- Advisor:
- Cremers, Daniel (Prof. Dr.)
- Referee:
- Cremers, Daniel (Prof. Dr.); Rodolà, Emanuele (Prof. Dr.); Ovsjanikov, Maks (Prof. Dr.)
- Language:
- en
- Subject group:
- DAT Datenverarbeitung, Informatik
- Keywords:
- shape analysis, computer vision, geometry processing, correspondence, interpolation, self-supervised learning
- Translated keywords:
- Formenanalyse, Bildverarbeitung, Korrespondenz, Interpolation
- TUM classification:
- DAT 760; DAT 770
- Abstract:
- Correspondence and interpolation of deformable 3D shapes are fundamental challenges in computer vision, with numerous potential applications. The main contributions of this dissertation comprise a number of specific practical algorithms, as well as general technical contributions in three major areas. We introduce shape deformation based on divergence-free vector fields, we perform multi-scale shape registration, and perform self-supervised learning on geometric data.
- Translated abstract:
- Das Berechnen von Korrespondenzen und Interpolationen deformierbarer 3D-Formen sind fundamentale Herausforderungen in der Computer Vision mit zahlreichen potenziellen Anwendungen. Die Hauptbeiträge dieser Dissertation behandeln verschiedene praktische Algorithmen und konkrete neue Formalismen in drei Hauptbereichen: der Deformation anhand von divergenzfreien Vektorfeldern, der mehrskaligen Registrierung von 3D-Formen sowie der Anwendung von selbstüberwachtem Lernen auf geometrische Daten.
- WWW:
- https://mediatum.ub.tum.de/?id=1730168
- Date of submission:
- 20.12.2023
- Oral examination:
- 09.10.2024
- File size:
- 96917782 bytes
- Pages:
- 218
- Urn (citeable URL):
- https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20241009-1730168-0-4
- Last change:
- 06.03.2025
BibTeX
Occurrences:
- mediaTUM GesamtbestandElektronische PrüfungsarbeitenSchoolTUM School of Computation, Information and Technology
- mediaTUM GesamtbestandHochschulbibliographie2024Schools und FakultätenTUM School of Computation, Information and TechnologyInformatik 9 - Lehrstuhl für Computer Vision and Artificial Intelligence (Prof. Cremers)