UVG-VPC: Voxelized Point Cloud Dataset for Visual Volumetric Video-based Coding

Guillaume Gautier; Alexandre Mercat; Louis Fréneau; Mikko Pitkänen; Jarno Vanne

doi:10.1109/QoMEX58391.2023.10178589

UVG-VPC: Voxelized Point Cloud Dataset for Visual Volumetric Video-based Coding

Guillaume Gautier, Alexandre Mercat, Louis Fréneau, Mikko Pitkänen, Jarno Vanne

Tietotekniikka

Tutkimustuotos: Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

3 Sitaatiot (Scopus)

171 Lataukset (Pure)

Abstrakti

Point cloud compression has become a crucial factor in immersive visual media processing and streaming. This paper presents a new open dataset called UVG-VPC for the development, evaluation, and validation of MPEG Visual Volumetric Video-based Coding (V3C) technology. The dataset is distributed under its own non-commercial license. It consists of 12 point cloud test video sequences of diverse characteristics with respect to the motion, RGB texture, 3D geometry, and surface occlusion of the points. Each sequence is 10 seconds long and comprises 250 frames captured at 25 frames per second. The sequences are voxelized with a geometry precision of 9 to 12 bits, and the voxel color attributes are represented as 8-bit RGB values. The dataset also includes associated normals that make it more suitable for evaluating point cloud compression solutions. The main objective of releasing the UVG-VPC dataset is to foster the development of V3C technologies and thereby shape the future in this field.

Alkuperäiskieli	Englanti
Otsikko	2023 15th International Conference on Quality of Multimedia Experience, QoMEX 2023
Kustantaja	IEEE
Sivut	244-247
Sivumäärä	4
ISBN (elektroninen)	979-8-3503-1173-0
DOI - pysyväislinkit	https://doi.org/10.1109/QoMEX58391.2023.10178589
Tila	Julkaistu - 2023
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	International Conference on Quality of Multimedia Experience - Ghent, Belgia Kesto: 20 kesäk. 2023 → 22 kesäk. 2023

Julkaisusarja

Nimi	International Conference on Quality of Multimedia Experience
ISSN (elektroninen)	2472-7814

Conference

Conference	International Conference on Quality of Multimedia Experience
Maa/Alue	Belgia
Kaupunki	Ghent
Ajanjakso	20/06/23 → 22/06/23

Rahoitus

This work was supported in part by the XR Simulation and Presence at the Cloud Edge (XR-SPACE) project led by Nokia and funded by Business Finland, and the Academy of Finland (decision no. 349216). This work was carried out with the support of Centre for Immersive Visual Technologies (CIVIT) research infrastructure, Tampere University, Finland. In addition, the authors wish to acknowledge CSC IT Center for Science, Finland, for computational and storage resources. This work was supported in part by the XR Simulation and Presence at the Cloud Edge (XR-SPACE) project led by Nokia and funded by Business Finland, and the Academy of Finland (decision no. 349216). ACKNOWLEDGMENT This work was carried out with the support of Centre for Immersive Visual Technologies (CIVIT) research infrastructure, Tampere University, Finland. In addition, the authors wish to acknowledge CSC – IT Center for Science, Finland, for computational and storage resources.

Julkaisufoorumi-taso

Jufo-taso 1

!!ASJC Scopus subject areas

Safety, Risk, Reliability and Quality
Media Technology

Pääsy asiakirjaan

10.1109/QoMEX58391.2023.10178589

2023_QoMEX_point_cloud_dataset
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Accepted author manuscript, 571 KBLisenssi: Unspecified

https://urn.fi/URN:NBN:fi:tuni-202310118763

Siteeraa tätä

Gautier, G., Mercat, A., Fréneau, L., Pitkänen, M., & Vanne, J. (2023). UVG-VPC: Voxelized Point Cloud Dataset for Visual Volumetric Video-based Coding. teoksessa 2023 15th International Conference on Quality of Multimedia Experience, QoMEX 2023 (Sivut 244-247). (International Conference on Quality of Multimedia Experience). IEEE. https://doi.org/10.1109/QoMEX58391.2023.10178589

@inproceedings{5bb9f2c3d44349a4b96518a251684da8,

title = "UVG-VPC: Voxelized Point Cloud Dataset for Visual Volumetric Video-based Coding",

abstract = "Point cloud compression has become a crucial factor in immersive visual media processing and streaming. This paper presents a new open dataset called UVG-VPC for the development, evaluation, and validation of MPEG Visual Volumetric Video-based Coding (V3C) technology. The dataset is distributed under its own non-commercial license. It consists of 12 point cloud test video sequences of diverse characteristics with respect to the motion, RGB texture, 3D geometry, and surface occlusion of the points. Each sequence is 10 seconds long and comprises 250 frames captured at 25 frames per second. The sequences are voxelized with a geometry precision of 9 to 12 bits, and the voxel color attributes are represented as 8-bit RGB values. The dataset also includes associated normals that make it more suitable for evaluating point cloud compression solutions. The main objective of releasing the UVG-VPC dataset is to foster the development of V3C technologies and thereby shape the future in this field.",

keywords = "Extended Reality (XR), Open dataset, point cloud, Video-based Point Cloud Compression (V-PCC), Visual Volumetric Video-based Coding (V3C)",

author = "Guillaume Gautier and Alexandre Mercat and Louis Fr{\'e}neau and Mikko Pitk{\"a}nen and Jarno Vanne",

note = "Funding Information: This work was supported in part by the XR Simulation and Presence at the Cloud Edge (XR-SPACE) project led by Nokia and funded by Business Finland, and the Academy of Finland (decision no. 349216). This work was carried out with the support of Centre for Immersive Visual Technologies (CIVIT) research infrastructure, Tampere University, Finland. In addition, the authors wish to acknowledge CSC IT Center for Science, Finland, for computational and storage resources. Funding Information: This work was supported in part by the XR Simulation and Presence at the Cloud Edge (XR-SPACE) project led by Nokia and funded by Business Finland, and the Academy of Finland (decision no. 349216). Funding Information: ACKNOWLEDGMENT This work was carried out with the support of Centre for Immersive Visual Technologies (CIVIT) research infrastructure, Tampere University, Finland. In addition, the authors wish to acknowledge CSC – IT Center for Science, Finland, for computational and storage resources. Publisher Copyright: {\textcopyright} 2023 IEEE.; International Conference on Quality of Multimedia Experience ; Conference date: 20-06-2023 Through 22-06-2023",

year = "2023",

doi = "10.1109/QoMEX58391.2023.10178589",

language = "English",

series = "International Conference on Quality of Multimedia Experience",

publisher = "IEEE",

pages = "244--247",

booktitle = "2023 15th International Conference on Quality of Multimedia Experience, QoMEX 2023",

address = "United States",

}

Gautier, G , Mercat, A , Fréneau, L, Pitkänen, M & Vanne, J 2023, UVG-VPC: Voxelized Point Cloud Dataset for Visual Volumetric Video-based Coding. julkaisussa 2023 15th International Conference on Quality of Multimedia Experience, QoMEX 2023. International Conference on Quality of Multimedia Experience, IEEE, Sivut 244-247, International Conference on Quality of Multimedia Experience, Ghent, Belgia, 20/06/23. https://doi.org/10.1109/QoMEX58391.2023.10178589

UVG-VPC: Voxelized Point Cloud Dataset for Visual Volumetric Video-based Coding. / Gautier, Guillaume ; Mercat, Alexandre ; Fréneau, Louis et al.
2023 15th International Conference on Quality of Multimedia Experience, QoMEX 2023. IEEE, 2023. s. 244-247 (International Conference on Quality of Multimedia Experience).

Tutkimustuotos: Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

TY - GEN

T1 - UVG-VPC

T2 - International Conference on Quality of Multimedia Experience

AU - Gautier, Guillaume

AU - Mercat, Alexandre

AU - Fréneau, Louis

AU - Pitkänen, Mikko

AU - Vanne, Jarno

N1 - Funding Information: This work was supported in part by the XR Simulation and Presence at the Cloud Edge (XR-SPACE) project led by Nokia and funded by Business Finland, and the Academy of Finland (decision no. 349216). This work was carried out with the support of Centre for Immersive Visual Technologies (CIVIT) research infrastructure, Tampere University, Finland. In addition, the authors wish to acknowledge CSC IT Center for Science, Finland, for computational and storage resources. Funding Information: This work was supported in part by the XR Simulation and Presence at the Cloud Edge (XR-SPACE) project led by Nokia and funded by Business Finland, and the Academy of Finland (decision no. 349216). Funding Information: ACKNOWLEDGMENT This work was carried out with the support of Centre for Immersive Visual Technologies (CIVIT) research infrastructure, Tampere University, Finland. In addition, the authors wish to acknowledge CSC – IT Center for Science, Finland, for computational and storage resources. Publisher Copyright: © 2023 IEEE.

PY - 2023

Y1 - 2023

N2 - Point cloud compression has become a crucial factor in immersive visual media processing and streaming. This paper presents a new open dataset called UVG-VPC for the development, evaluation, and validation of MPEG Visual Volumetric Video-based Coding (V3C) technology. The dataset is distributed under its own non-commercial license. It consists of 12 point cloud test video sequences of diverse characteristics with respect to the motion, RGB texture, 3D geometry, and surface occlusion of the points. Each sequence is 10 seconds long and comprises 250 frames captured at 25 frames per second. The sequences are voxelized with a geometry precision of 9 to 12 bits, and the voxel color attributes are represented as 8-bit RGB values. The dataset also includes associated normals that make it more suitable for evaluating point cloud compression solutions. The main objective of releasing the UVG-VPC dataset is to foster the development of V3C technologies and thereby shape the future in this field.

AB - Point cloud compression has become a crucial factor in immersive visual media processing and streaming. This paper presents a new open dataset called UVG-VPC for the development, evaluation, and validation of MPEG Visual Volumetric Video-based Coding (V3C) technology. The dataset is distributed under its own non-commercial license. It consists of 12 point cloud test video sequences of diverse characteristics with respect to the motion, RGB texture, 3D geometry, and surface occlusion of the points. Each sequence is 10 seconds long and comprises 250 frames captured at 25 frames per second. The sequences are voxelized with a geometry precision of 9 to 12 bits, and the voxel color attributes are represented as 8-bit RGB values. The dataset also includes associated normals that make it more suitable for evaluating point cloud compression solutions. The main objective of releasing the UVG-VPC dataset is to foster the development of V3C technologies and thereby shape the future in this field.

KW - Extended Reality (XR)

KW - Open dataset

KW - point cloud

KW - Video-based Point Cloud Compression (V-PCC)

KW - Visual Volumetric Video-based Coding (V3C)

U2 - 10.1109/QoMEX58391.2023.10178589

DO - 10.1109/QoMEX58391.2023.10178589

M3 - Conference contribution

AN - SCOPUS:85167353197

T3 - International Conference on Quality of Multimedia Experience

SP - 244

EP - 247

BT - 2023 15th International Conference on Quality of Multimedia Experience, QoMEX 2023

PB - IEEE

Y2 - 20 June 2023 through 22 June 2023

ER -

UVG-VPC: Voxelized Point Cloud Dataset for Visual Volumetric Video-based Coding

Abstrakti

Julkaisusarja

Conference

Rahoitus

Julkaisufoorumi-taso

!!ASJC Scopus subject areas

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä