Unsupervised Description of 3D Shapes by Superquadrics Using Deep Learning
- The decomposition of 3D shapes into simple yet representative components is a very intriguing topic in computer vision as it is very useful for many possible applications. Superquadrics may be used with benefit to obtain an implicit representation of the 3D shapes, as they allow to represent a wide range of possible forms by few parameters. However, in the computation of the shape representation, there is often an intricate trade-off between the variation of the represented geometric forms and the accuracy in such implicit approaches. In this paper, we propose an improved loss function, and we introduce beneficial computational techniques. By comparing results obtained by our new technique to the baseline method, we demonstrate that our results are more reliable and accurate, as well as much faster to obtain.
Author: | Mahmoud Eltaher, Michael BreußGND |
---|---|
DOI: | https://doi.org/10.1007/978-981-19-7867-8_9 |
ISBN: | 978-981-19-7866-1 |
ISSN: | 978-981-19-7867-8 |
Title of the source (English): | Computer Vision and Machine Intelligence : Proceedings of CVMI 2022 |
Publisher: | Springer |
Place of publication: | Singapore |
Document Type: | Conference publication peer-reviewed |
Language: | English |
Year of publication: | 2023 |
Tag: | Implicit shape representation Superquadrics Deep learning 3D shape description |
First Page: | 95 |
Last Page: | 107 |
Series ; volume number: | Lecture Notes in Networks and Systems book series (LNNS) ; volume 586 |
Faculty/Chair: | Fakultät 1 MINT - Mathematik, Informatik, Physik, Elektro- und Informationstechnik / FG Angewandte Mathematik |