Deep Learning Parametrization for B-Spline Curve Approximation
- In this paper we present a method using deep learning to compute parametrizations for B-spline curve approximation. Existing methods consider the computation of parametric values and a knot vector as separate problems. We propose to train interdependent deep neural networks to predict parametric values and knots. We show that it is possible to include B-spline curve approximation directly into the neural network architecture. The resulting parametrizations yield tight approximations and are able to outperform state-of-the-art methods.
Author: | Pascal Laube, Matthias O. FranzORCiDGND, Georg UmlaufORCiDGND |
---|---|
DOI: | https://doi.org/10.1109/3DV.2018.00084 |
ISSN: | 2475-7888 |
Parent Title (English): | International Conference on 3D Vision (3DV), 5-8 Sept. 2018, Verona, Italy |
Publisher: | IEEE |
Document Type: | Conference Proceeding |
Language: | English |
Year of Publication: | 2018 |
Release Date: | 2019/01/18 |
First Page: | 691 |
Last Page: | 699 |
Note: | Volltextzugriff im Campusnetz der Hochschule Konstanz möglich (Datenbank IEEE Xplore) |
Institutes: | Institut für Optische Systeme - IOS |
Open Access?: | Nein |
Licence (German): | ![]() |