Contrastive Learning for 3D Point Clouds Classification and Shape Completion

In this paper, we present the idea of Self Supervised learning on the shape completion and classification of point clouds. Most 3D shape completion pipelines utilize AutoEncoders to extract features from point clouds used in downstream tasks such as classification, segmentation, detection, and other...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Danish Nazir, Muhammad Zeshan Afzal, Alain Pagani, Marcus Liwicki, Didier Stricker
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	point cloud classification point cloud shape completion AutoEncoders contrastive AutoEncoders contrasitive learning for point clouds self-supervised learning for point cloud shape completion Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/0692d70bba7b47738add93318f10650f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0692d70bba7b47738add93318f10650f
record_format	dspace
spelling	oai:doaj.org-article:0692d70bba7b47738add93318f10650f2021-11-11T19:19:12ZContrastive Learning for 3D Point Clouds Classification and Shape Completion10.3390/s212173921424-8220https://doaj.org/article/0692d70bba7b47738add93318f10650f2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7392https://doaj.org/toc/1424-8220In this paper, we present the idea of Self Supervised learning on the shape completion and classification of point clouds. Most 3D shape completion pipelines utilize AutoEncoders to extract features from point clouds used in downstream tasks such as classification, segmentation, detection, and other related applications. Our idea is to add contrastive learning into AutoEncoders to encourage global feature learning of the point cloud classes. It is performed by optimizing triplet loss. Furthermore, local feature representations learning of point cloud is performed by adding the Chamfer distance function. To evaluate the performance of our approach, we utilize the PointNet classifier. We also extend the number of classes for evaluation from 4 to 10 to show the generalization ability of the learned features. Based on our results, embeddings generated from the contrastive AutoEncoder enhances shape completion and classification performance from <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>84.2</mn><mo>%</mo></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>84.9</mn><mo>%</mo></mrow></semantics></math></inline-formula> of point clouds achieving the state-of-the-art results with 10 classes.Danish NazirMuhammad Zeshan AfzalAlain PaganiMarcus LiwickiDidier StrickerMDPI AGarticlepoint cloud classificationpoint cloud shape completionAutoEncoderscontrastive AutoEncoderscontrasitive learning for point cloudsself-supervised learning for point cloud shape completionChemical technologyTP1-1185ENSensors, Vol 21, Iss 7392, p 7392 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	point cloud classification point cloud shape completion AutoEncoders contrastive AutoEncoders contrasitive learning for point clouds self-supervised learning for point cloud shape completion Chemical technology TP1-1185
spellingShingle	point cloud classification point cloud shape completion AutoEncoders contrastive AutoEncoders contrasitive learning for point clouds self-supervised learning for point cloud shape completion Chemical technology TP1-1185 Danish Nazir Muhammad Zeshan Afzal Alain Pagani Marcus Liwicki Didier Stricker Contrastive Learning for 3D Point Clouds Classification and Shape Completion
description	In this paper, we present the idea of Self Supervised learning on the shape completion and classification of point clouds. Most 3D shape completion pipelines utilize AutoEncoders to extract features from point clouds used in downstream tasks such as classification, segmentation, detection, and other related applications. Our idea is to add contrastive learning into AutoEncoders to encourage global feature learning of the point cloud classes. It is performed by optimizing triplet loss. Furthermore, local feature representations learning of point cloud is performed by adding the Chamfer distance function. To evaluate the performance of our approach, we utilize the PointNet classifier. We also extend the number of classes for evaluation from 4 to 10 to show the generalization ability of the learned features. Based on our results, embeddings generated from the contrastive AutoEncoder enhances shape completion and classification performance from <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>84.2</mn><mo>%</mo></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>84.9</mn><mo>%</mo></mrow></semantics></math></inline-formula> of point clouds achieving the state-of-the-art results with 10 classes.
format	article
author	Danish Nazir Muhammad Zeshan Afzal Alain Pagani Marcus Liwicki Didier Stricker
author_facet	Danish Nazir Muhammad Zeshan Afzal Alain Pagani Marcus Liwicki Didier Stricker
author_sort	Danish Nazir
title	Contrastive Learning for 3D Point Clouds Classification and Shape Completion
title_short	Contrastive Learning for 3D Point Clouds Classification and Shape Completion
title_full	Contrastive Learning for 3D Point Clouds Classification and Shape Completion
title_fullStr	Contrastive Learning for 3D Point Clouds Classification and Shape Completion
title_full_unstemmed	Contrastive Learning for 3D Point Clouds Classification and Shape Completion
title_sort	contrastive learning for 3d point clouds classification and shape completion
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/0692d70bba7b47738add93318f10650f
work_keys_str_mv	AT danishnazir contrastivelearningfor3dpointcloudsclassificationandshapecompletion AT muhammadzeshanafzal contrastivelearningfor3dpointcloudsclassificationandshapecompletion AT alainpagani contrastivelearningfor3dpointcloudsclassificationandshapecompletion AT marcusliwicki contrastivelearningfor3dpointcloudsclassificationandshapecompletion AT didierstricker contrastivelearningfor3dpointcloudsclassificationandshapecompletion
_version_	1718431508525481984

Contrastive Learning for 3D Point Clouds Classification and Shape Completion

Ejemplares similares