Machine learning methods for reverse engineering of defective structured surfaces
- Pascal Laube presents machine learning approaches for three key problems of reverse engineering of defective structured surfaces: parametrization of curves and surfaces, geometric primitive classification and inpainting of high-resolution textures. The proposed methods aim to improve the reconstruction quality while further automating the process. The contributions demonstrate that machine learning can be a viable part of the CAD reverse engineering pipeline.
| Author: | Pascal Laube |
|---|---|
| DOI: | https://doi.org/10.1007/978-3-658-29017-7 |
| ISBN: | 978-3-658-29017-7 |
| ISBN: | 978-3-658-29016-0 |
| Parent Title (German): | Schriftenreihe der Institute für Systemdynamik (ISD) und optische Systeme (IOS) |
| Publisher: | Springer Vieweg |
| Place of publication: | Wiesbaden |
| Advisor: | Georg Umlauf, Oliver Deussen |
| Document Type: | Doctoral Thesis |
| Language: | English |
| Year of Publication: | 2020 |
| Granting Institution: | Universität Konstanz |
| Date of final exam: | 2019/07/25 |
| Release Date: | 2020/01/21 |
| Page Number: | 160 |
| Institutes: | Institut für Optische Systeme - IOS |
| Relevance: | Abgeschlossene Dissertation |
| Open Access?: | Nein |
| Licence (German): |  Urheberrechtlich geschützt |
