Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Contrastive Learning for 3D Point Clouds Classification and Shape Completion
Department of Computer Science, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany; Mindgarage, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany.
Department of Computer Science, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany; Mindgarage, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany; German Research Institute for Artificial Intelligence (DFKI), 67663 Kaiserslautern, Germany.
German Research Institute for Artificial Intelligence (DFKI), 67663 Kaiserslautern, Germany.
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0003-4029-6574
Show others and affiliations
2021 (English)In: Sensors, E-ISSN 1424-8220, Vol. 21, no 21, article id 7392Article in journal (Refereed) Published
Abstract [en]

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 84.2% to 84.9% of point clouds achieving the state-of-the-art results with 10 classes.

Place, publisher, year, edition, pages
MDPI, 2021. Vol. 21, no 21, article id 7392
National Category
Computer Sciences
Research subject
Machine Learning
Identifiers
URN: urn:nbn:se:ltu:diva-87812DOI: 10.3390/s21217392ISI: 000718503200001PubMedID: 34770698Scopus ID: 2-s2.0-85118549838OAI: oai:DiVA.org:ltu-87812DiVA, id: diva2:1609161
Note

Validerad;2021;Nivå 2;2021-11-08 (johcin)

Available from: 2021-11-07 Created: 2021-11-07 Last updated: 2022-02-10Bibliographically approved

Open Access in DiVA

fulltext(16196 kB)594 downloads
File information
File name FULLTEXT01.pdfFile size 16196 kBChecksum SHA-512
20063740c3b227d01aa75b1bd9263cd85d5f303ad40f7802a1783d54d07acd13524f27ad8ba3a83846e3f6ae488600de8d10a8deb4dbce41fbc8fdc97d27deef
Type fulltextMimetype application/pdf

Other links

Publisher's full textPubMedScopus

Authority records

Liwicki, Marcus

Search in DiVA

By author/editor
Liwicki, Marcus
By organisation
Embedded Internet Systems Lab
In the same journal
Sensors
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 594 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 117 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf