Repository logo
 
Publication

Deep Learning-based Point Cloud Geometry Coding with Resolution Scalability

datacite.subject.sdg03:Saúde de Qualidade
datacite.subject.sdg10:Reduzir as Desigualdades
datacite.subject.sdg11:Cidades e Comunidades Sustentáveis
dc.contributor.authorGuarda, André F. R.
dc.contributor.authorRodrigues, Nuno M. M.
dc.contributor.authorPereira, Fernando
dc.date.accessioned2025-07-22T15:31:03Z
dc.date.available2025-07-22T15:31:03Z
dc.date.issued2020-09
dc.descriptionEISBN - 978-1-7281-9320-5
dc.descriptionArticle number - 9287060; Conference date - 21 September 2020 - 24 September 2020; Conference code - 165866
dc.description.abstractPoint clouds are a 3D visual representation format that has recently become fundamentally important for immersive and interactive multimedia applications. Considering the high number of points of practically relevant point clouds, and their increasing market demand, efficient point cloud coding has become a vital research topic. In addition, scalability is an important feature for point cloud coding, especially for real-time applications, where the fast and rate efficient access to a decoded point cloud is important; however, this issue is still rather unexplored in the literature. In this context, this paper proposes a novel deep learning-based point cloud geometry coding solution with resolution scalability via interlaced sub-sampling. As additional layers are decoded, the number of points in the reconstructed point cloud increases as well as the overall quality. Experimental results show that the proposed scalable point cloud geometry coding solution outperforms the recent MPEG Geometry-based Point Cloud Compression standard which is much less scalable.eng
dc.description.sponsorshipThis work was funded by Fundação para a Ciência e Tecnologia (FCT), Portugal, Ph.D. Grant SFRH/BD/118218/2016, by FCT/MEC through national funds and when applicable co-funded by EU funds under the project UIDB/EEA/50008/2020.
dc.identifier.citationA. F. R. Guarda, N. M. M. Rodrigues and F. Pereira, "Deep Learning-based Point Cloud Geometry Coding with Resolution Scalability," 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP), Tampere, Finland, 2020, pp. 1-6, doi: https://doi.org/10.1109/MMSP48831.2020.9287060.
dc.identifier.doi10.1109/mmsp48831.2020.9287060
dc.identifier.eissn2473-3628
dc.identifier.isbn978-1-7281-9323-6
dc.identifier.isbn978-1-7281-9320-5
dc.identifier.issn2163-3517
dc.identifier.urihttp://hdl.handle.net/10400.8/13753
dc.language.isoeng
dc.peerreviewedyes
dc.publisherIEEE Canada
dc.relationEfficient lossy and lossless compression of point clouds
dc.relation.hasversionhttps://ieeexplore.ieee.org/document/9287060
dc.relation.ispartof2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)
dc.rights.uriN/A
dc.subjectpoint cloud coding
dc.subjectdeep learning
dc.subjectscalable coding
dc.subjectresolution scalability
dc.subjectinterlaced sampling
dc.titleDeep Learning-based Point Cloud Geometry Coding with Resolution Scalabilityeng
dc.typeconference paper
dspace.entity.typePublication
oaire.awardTitleEfficient lossy and lossless compression of point clouds
oaire.awardURIhttp://hdl.handle.net/10400.8/12910
oaire.citation.conferenceDate2020-09
oaire.citation.conferencePlaceTampere, Finland
oaire.citation.titleIEEE 22nd International Workshop on Multimedia Signal Processing, MMSP 2020
oaire.fundingStreamOE
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameM. M. Rodrigues
person.givenNameNuno
person.identifier.orcid0000-0001-9536-1017
person.identifier.scopus-author-id7006052345
relation.isAuthorOfPublicationb4ebe652-7f0e-4e67-adb0-d5ea29fc9e69
relation.isAuthorOfPublication.latestForDiscoveryb4ebe652-7f0e-4e67-adb0-d5ea29fc9e69
relation.isProjectOfPublicationd619b8c6-7ef9-4635-98fd-a9a7be25e5f8
relation.isProjectOfPublication.latestForDiscoveryd619b8c6-7ef9-4635-98fd-a9a7be25e5f8

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Deep Learning-based Point Cloud Geometry Coding with Resolution Scalability.pdf
Size:
1.11 MB
Format:
Adobe Portable Document Format
Description:
Point clouds are a 3D visual representation format that has recently become fundamentally important for immersive and interactive multimedia applications. Considering the high number of points of practically relevant point clouds, and their increasing market demand, efficient point cloud coding has become a vital research topic. In addition, scalability is an important feature for point cloud coding, especially for real-time applications, where the fast and rate efficient access to a decoded point cloud is important; however, this issue is still rather unexplored in the literature. In this context, this paper proposes a novel deep learning-based point cloud geometry coding solution with resolution scalability via interlaced sub-sampling. As additional layers are decoded, the number of points in the reconstructed point cloud increases as well as the overall quality. Experimental results show that the proposed scalable point cloud geometry coding solution outperforms the recent MPEG Geometry-based Point Cloud Compression standard which is much less scalable.
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.32 KB
Format:
Item-specific license agreed upon to submission
Description: