Deep Distance Metric Learning for Similarity Preserving Embedding of Point Clouds

Ahmed Abouelazm, Igor Vozniak, Nils Lipp, Pavel Astreika, Christian Mueller

2023

Abstract

Point cloud processing and 3D model retrieval methods have received a lot of interest as a result of the recent advancement in deep learning, computing hardware, and a wide range of available 3D sensors. Many state-of-the-art approaches utilize distance metric learning for solving the 3D model retrieval problem. However, the majority of these approaches disregard the variation in shape and properties of instances belonging to the same class known as intra-class variance, and focus on semantic labels as a measure of relevance. In this work, we present two novel loss functions for similarity-preserving point cloud embedding, in which the distance between point clouds in the embedding space is directly proportional to the ground truth distance between them using a similarity or distance measure. The building block of both loss functions is the forward passing of n-pair input point clouds through a Siamese network. We utilize ModelNet 10 dataset in the course of numerical evaluations under classification and mean average precision evaluation metrics. The reported quantitative and qualitative results demonstrate enhancement in retrieved models both quantitatively and qualitatively by a significant margin.

Paper Citation

in Harvard Style

Abouelazm A., Vozniak I., Lipp N., Astreika P. and Mueller C. (2023). Deep Distance Metric Learning for Similarity Preserving Embedding of Point Clouds. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 570-581. DOI: 10.5220/0011627100003417

in Bibtex Style

@conference{visapp23,
author={Ahmed Abouelazm and Igor Vozniak and Nils Lipp and Pavel Astreika and Christian Mueller},
title={Deep Distance Metric Learning for Similarity Preserving Embedding of Point Clouds},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={570-581},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011627100003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - Deep Distance Metric Learning for Similarity Preserving Embedding of Point Clouds
SN - 978-989-758-634-7
AU - Abouelazm A.
AU - Vozniak I.
AU - Lipp N.
AU - Astreika P.
AU - Mueller C.
PY - 2023
SP - 570
EP - 581
DO - 10.5220/0011627100003417
PB - SciTePress