Category-level Part-based 3D Object Non-rigid Registration

Diego Rodriguez, Florian Huber, Sven Behnke

2022

Abstract

In this paper, we propose a novel approach for registering objects in a non-rigid manner based on decomposed parts of an object category. By performing part-based registration, the deforming points match better local geometric structures of the observed instance. Moreover, the knowledge acquired of an object part can be transferred to different object categories that share the same decomposed part. This is possible because the registration is based on a learned latent space that encodes typical geometrical variations of each part independently. We evaluate our approach extensively on different object categories and demonstrate its robustness against outliers, noise and misalignments of the object pose.

Paper Citation

in Harvard Style

Rodriguez D., Huber F. and Behnke S. (2022). Category-level Part-based 3D Object Non-rigid Registration. 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, SciTePress, pages 795-802. DOI: 10.5220/0010761800003124

in Bibtex Style

@conference{visapp22,
author={Diego Rodriguez and Florian Huber and Sven Behnke},
title={Category-level Part-based 3D Object Non-rigid Registration},
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={795-802},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010761800003124},
isbn={978-989-758-555-5},
}

in EndNote Style

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 - Category-level Part-based 3D Object Non-rigid Registration
SN - 978-989-758-555-5
AU - Rodriguez D.
AU - Huber F.
AU - Behnke S.
PY - 2022
SP - 795
EP - 802
DO - 10.5220/0010761800003124
PB - SciTePress