loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Clara Holzhüter ; Florian Teich and Florentin Wörgötter

Affiliation: III. Physikalisches Institut, Georg-August University, Friedrich-Hundt Platz 1, Göttingen, Germany

Keyword(s): 3D, Computer Vision, Classification, Point Clouds, Segmentation, Graph Convolution.

Abstract: 3D object classification is involved in many computer vision pipelines such as autonomous driving or robotics. However, the irregular format of 3D data makes it challenging to develop suitable deep learning architectures. This paper proposes CompointNet, a graph convolutional network architecture, which performs 3D object classification by means of part decomposition. Our model consumes a 3D point cloud in the form of a part graph which is constructed from segmented 3D shapes. The model learns a global descriptor by hierarchically aggregating neighbourhood information using simple graph convolutions. To capture both local and global information, a global classification method processing each point separately is combined with our part graph based approach into a hybrid version of CompointNet. We compare our approach to several state-of-the art methods and demonstrate competitive performance. Particularly, in terms of per class accuracy, our hybrid approach outperforms the compared met hods. The proposed hybrid variants achieve a high classification accuracy, while being much more efficient than those benchmark models with a comparable performance. The conducted experiments show that part based approaches levering structural information about a 3D object, indeed, can improve the classification performance of 3D deep learning models. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.149.235.66

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Holzhüter, C.; Teich, F. and Wörgötter, F. (2022). Segmentation Improves 3D Object Classification in Graph Convolutional Networks. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5; ISSN 2184-4321, SciTePress, pages 290-298. DOI: 10.5220/0010778100003124

@conference{visapp22,
author={Clara Holzhüter. and Florian Teich. and Florentin Wörgötter.},
title={Segmentation Improves 3D Object Classification in Graph Convolutional Networks},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={290-298},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010778100003124},
isbn={978-989-758-555-5},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Segmentation Improves 3D Object Classification in Graph Convolutional Networks
SN - 978-989-758-555-5
IS - 2184-4321
AU - Holzhüter, C.
AU - Teich, F.
AU - Wörgötter, F.
PY - 2022
SP - 290
EP - 298
DO - 10.5220/0010778100003124
PB - SciTePress