Improving Free-Viewpoint Video Content Production Using RGB-Camera-Based Skeletal Tracking

Andrew MacQuarrie; Anthony Steed

doi:10.1109/VRW50115.2020.00238

Improving Free-Viewpoint Video Content Production Using RGB-Camera-Based Skeletal Tracking

Andrew MacQuarrie
, Anthony Steed

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

2 Citations (Scopus)

Abstract

Free-Viewpoint Video (FVV) is a type of volumetric content in which an animated, video-textured 3D mesh of a character performance is constructed using data from an array of cameras. Previous work has demonstrated excellent results when creating motion graphs from FVV content, but these techniques are often prohibitively expensive in practice. We propose the use of skeletons to identify cut points between FVV clips, allowing a minimal set of frames to be processed into a 3D mesh. While our method performed with 2.8% poorer accuracy than the state-of-the-art for our synthetic dataset, cost and processing time requirements are dramatically reduced.

Original language	English
Title of host publication	Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	775-776
Number of pages	2
ISBN (Electronic)	9781728165325
DOIs	https://doi.org/10.1109/VRW50115.2020.00238
Publication status	Published - Mar 2020
Event	2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020 - Atlanta, United States Duration: 22 Mar 2020 → 26 Mar 2020

Publication series

Name	Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020

Conference

Conference	2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020
Country/Territory	United States
City	Atlanta
Period	22/03/20 → 26/03/20

Bibliographical note

Funding Information:
This work was supported in part by grants EP/N509577/1 and EP/M029263/1 from the UK Engineering and Physical Sciences Research Council (EPSRC). The authors would like to thank Dimension Studio and Digital Catapult for their support.

Publisher Copyright:
© 2020 IEEE.

Research Groups and Themes

Bristol Interaction Group

Access to Document

10.1109/VRW50115.2020.00238

Handle.net

Persistent link

Cite this

MacQuarrie, A., & Steed, A. (2020). Improving Free-Viewpoint Video Content Production Using RGB-Camera-Based Skeletal Tracking. In Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020 (pp. 775-776). Article 9090565 (Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/VRW50115.2020.00238

MacQuarrie, Andrew ; Steed, Anthony. / Improving Free-Viewpoint Video Content Production Using RGB-Camera-Based Skeletal Tracking. Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020. Institute of Electrical and Electronics Engineers (IEEE), 2020. pp. 775-776 (Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020).

@inproceedings{8d49dfe1ec9f4f43880295a778c5d931,

title = "Improving Free-Viewpoint Video Content Production Using RGB-Camera-Based Skeletal Tracking",

abstract = "Free-Viewpoint Video (FVV) is a type of volumetric content in which an animated, video-textured 3D mesh of a character performance is constructed using data from an array of cameras. Previous work has demonstrated excellent results when creating motion graphs from FVV content, but these techniques are often prohibitively expensive in practice. We propose the use of skeletons to identify cut points between FVV clips, allowing a minimal set of frames to be processed into a 3D mesh. While our method performed with 2.8\% poorer accuracy than the state-of-the-art for our synthetic dataset, cost and processing time requirements are dramatically reduced.",

author = "Andrew MacQuarrie and Anthony Steed",

note = "Funding Information: This work was supported in part by grants EP/N509577/1 and EP/M029263/1 from the UK Engineering and Physical Sciences Research Council (EPSRC). The authors would like to thank Dimension Studio and Digital Catapult for their support. Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020 ; Conference date: 22-03-2020 Through 26-03-2020",

year = "2020",

month = mar,

doi = "10.1109/VRW50115.2020.00238",

language = "English",

series = "Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "775--776",

booktitle = "Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020",

address = "United States",

}

MacQuarrie, A & Steed, A 2020, Improving Free-Viewpoint Video Content Production Using RGB-Camera-Based Skeletal Tracking. in Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020., 9090565, Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020, Institute of Electrical and Electronics Engineers (IEEE), pp. 775-776, 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020, Atlanta, United States, 22/03/20. https://doi.org/10.1109/VRW50115.2020.00238

Improving Free-Viewpoint Video Content Production Using RGB-Camera-Based Skeletal Tracking. / MacQuarrie, Andrew; Steed, Anthony.
Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020. Institute of Electrical and Electronics Engineers (IEEE), 2020. p. 775-776 9090565 (Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Improving Free-Viewpoint Video Content Production Using RGB-Camera-Based Skeletal Tracking

AU - MacQuarrie, Andrew

AU - Steed, Anthony

N1 - Funding Information: This work was supported in part by grants EP/N509577/1 and EP/M029263/1 from the UK Engineering and Physical Sciences Research Council (EPSRC). The authors would like to thank Dimension Studio and Digital Catapult for their support. Publisher Copyright: © 2020 IEEE.

PY - 2020/3

Y1 - 2020/3

N2 - Free-Viewpoint Video (FVV) is a type of volumetric content in which an animated, video-textured 3D mesh of a character performance is constructed using data from an array of cameras. Previous work has demonstrated excellent results when creating motion graphs from FVV content, but these techniques are often prohibitively expensive in practice. We propose the use of skeletons to identify cut points between FVV clips, allowing a minimal set of frames to be processed into a 3D mesh. While our method performed with 2.8% poorer accuracy than the state-of-the-art for our synthetic dataset, cost and processing time requirements are dramatically reduced.

AB - Free-Viewpoint Video (FVV) is a type of volumetric content in which an animated, video-textured 3D mesh of a character performance is constructed using data from an array of cameras. Previous work has demonstrated excellent results when creating motion graphs from FVV content, but these techniques are often prohibitively expensive in practice. We propose the use of skeletons to identify cut points between FVV clips, allowing a minimal set of frames to be processed into a 3D mesh. While our method performed with 2.8% poorer accuracy than the state-of-the-art for our synthetic dataset, cost and processing time requirements are dramatically reduced.

UR - https://www.scopus.com/pages/publications/85085379427

U2 - 10.1109/VRW50115.2020.00238

DO - 10.1109/VRW50115.2020.00238

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:85085379427

T3 - Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020

SP - 775

EP - 776

BT - Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020

Y2 - 22 March 2020 through 26 March 2020

ER -

MacQuarrie A, Steed A. Improving Free-Viewpoint Video Content Production Using RGB-Camera-Based Skeletal Tracking. In Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020. Institute of Electrical and Electronics Engineers (IEEE). 2020. p. 775-776. 9090565. (Proceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020). doi: 10.1109/VRW50115.2020.00238

Improving Free-Viewpoint Video Content Production Using RGB-Camera-Based Skeletal Tracking

Abstract

Publication series

Conference

Bibliographical note

Research Groups and Themes

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this