NR-GVQM: a no reference gaming video quality metric

Saman Zadtootaghaj; Nabajeet Barman; Steven Schmidt; Maria Martini; Sebastian M├Âller

NR-GVQM: a no reference gaming video quality metric

Saman Zadtootaghaj
, Nabajeet Barman
, Steven Schmidt
, Maria Martini
, Sebastian M├Âller

Research output: Contribution to conference › Paper › peer-review

Abstract

Gaming as a popular system has recently expanded the associated services, by stepping into live streaming services. Live gaming video streaming is not only limited to cloud gaming services, such as Geforce Now, but also include passive streaming, where the players' gameplay is streamed both live and ondemand over services such as Twitch.tv and YouTubeGaming. So far, in terms of gaming video quality assessment, typical video quality assessment methods have been used. However, their performance remains quite unsatisfactory. In this paper, we present a new No Reference (NR) gaming video quality metric called NR-GVQM with performance comparable to state-of-the-art Full Reference (FR) metrics. NR-GVQM is designed by training a Support Vector Regression (SVR) with the Gaussian kernel using nine frame-level indexes such as naturalness and blockiness as input features and Video Multimethod Assessment Fusion (VMAF) scores as the ground truth. Our results based on a publicly available dataset of gaming videos are shown to have a correlation score of 0.98 with VMAF and 0.89 with MOS scores. We further present two approaches to reduce computational complexity.

Original language	English
Publication status	Published - Dec 2018
Event	2018 IEEE International Symposium on Multimedia (ISM) - Taichung City, Taiwan Duration: 10 Dec 2018 → 12 Dec 2018

Conference

Conference	2018 IEEE International Symposium on Multimedia (ISM)
Period	10/12/18 → 12/12/18

Bibliographical note

Note: Published in: 2018 IEEE International Symposium on Multimedia (ISM). Piscataway, NJ : IEEE. ISBN 9781538668580.

Organising Body: The Institute of Electrical and Electronics Engineers

Keywords

Computer science and informatics

Access to Document

https://doi.org/10.1109/ISM.2018.00031

1 Conference contribution

NR-GVQM: a no reference gaming video quality metric
Zadtootaghaj, S., Barman, N., Schmidt, S., Martini, M. & M├Âller, S., Dec 2018, Published in: 2018 IEEE International Symposium on Multimedia (ISM). Piscataway, NJ : IEEE. ISBN 9781538668580. Organising Body: The Institute of Electrical and Electronics Engineers Organising Body: The Institute of Electrical and Electronics Engineers.
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Cite this

@conference{1fc7b66c4be94368a2a8ceb464bac04b,

title = "NR-GVQM: a no reference gaming video quality metric",

abstract = "Gaming as a popular system has recently expanded the associated services, by stepping into live streaming services. Live gaming video streaming is not only limited to cloud gaming services, such as Geforce Now, but also include passive streaming, where the players' gameplay is streamed both live and ondemand over services such as Twitch.tv and YouTubeGaming. So far, in terms of gaming video quality assessment, typical video quality assessment methods have been used. However, their performance remains quite unsatisfactory. In this paper, we present a new No Reference (NR) gaming video quality metric called NR-GVQM with performance comparable to state-of-the-art Full Reference (FR) metrics. NR-GVQM is designed by training a Support Vector Regression (SVR) with the Gaussian kernel using nine frame-level indexes such as naturalness and blockiness as input features and Video Multimethod Assessment Fusion (VMAF) scores as the ground truth. Our results based on a publicly available dataset of gaming videos are shown to have a correlation score of 0.98 with VMAF and 0.89 with MOS scores. We further present two approaches to reduce computational complexity.",

keywords = "Computer science and informatics",

author = "Saman Zadtootaghaj and Nabajeet Barman and Steven Schmidt and Maria Martini and Sebastian M├{\^A}ller",

note = "Note: Published in: 2018 IEEE International Symposium on Multimedia (ISM). Piscataway, NJ : IEEE. ISBN 9781538668580. Organising Body: The Institute of Electrical and Electronics Engineers; 2018 IEEE International Symposium on Multimedia (ISM) ; Conference date: 10-12-2018 Through 12-12-2018",

year = "2018",

month = dec,

language = "English",

}

TY - CONF

T1 - NR-GVQM

T2 - 2018 IEEE International Symposium on Multimedia (ISM)

AU - Zadtootaghaj, Saman

AU - Barman, Nabajeet

AU - Schmidt, Steven

AU - Martini, Maria

AU - M├Âller, Sebastian

N1 - Note: Published in: 2018 IEEE International Symposium on Multimedia (ISM). Piscataway, NJ : IEEE. ISBN 9781538668580. Organising Body: The Institute of Electrical and Electronics Engineers

PY - 2018/12

Y1 - 2018/12

N2 - Gaming as a popular system has recently expanded the associated services, by stepping into live streaming services. Live gaming video streaming is not only limited to cloud gaming services, such as Geforce Now, but also include passive streaming, where the players' gameplay is streamed both live and ondemand over services such as Twitch.tv and YouTubeGaming. So far, in terms of gaming video quality assessment, typical video quality assessment methods have been used. However, their performance remains quite unsatisfactory. In this paper, we present a new No Reference (NR) gaming video quality metric called NR-GVQM with performance comparable to state-of-the-art Full Reference (FR) metrics. NR-GVQM is designed by training a Support Vector Regression (SVR) with the Gaussian kernel using nine frame-level indexes such as naturalness and blockiness as input features and Video Multimethod Assessment Fusion (VMAF) scores as the ground truth. Our results based on a publicly available dataset of gaming videos are shown to have a correlation score of 0.98 with VMAF and 0.89 with MOS scores. We further present two approaches to reduce computational complexity.

AB - Gaming as a popular system has recently expanded the associated services, by stepping into live streaming services. Live gaming video streaming is not only limited to cloud gaming services, such as Geforce Now, but also include passive streaming, where the players' gameplay is streamed both live and ondemand over services such as Twitch.tv and YouTubeGaming. So far, in terms of gaming video quality assessment, typical video quality assessment methods have been used. However, their performance remains quite unsatisfactory. In this paper, we present a new No Reference (NR) gaming video quality metric called NR-GVQM with performance comparable to state-of-the-art Full Reference (FR) metrics. NR-GVQM is designed by training a Support Vector Regression (SVR) with the Gaussian kernel using nine frame-level indexes such as naturalness and blockiness as input features and Video Multimethod Assessment Fusion (VMAF) scores as the ground truth. Our results based on a publicly available dataset of gaming videos are shown to have a correlation score of 0.98 with VMAF and 0.89 with MOS scores. We further present two approaches to reduce computational complexity.

KW - Computer science and informatics

M3 - Paper

Y2 - 10 December 2018 through 12 December 2018

ER -

NR-GVQM: a no reference gaming video quality metric

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Research output

NR-GVQM: a no reference gaming video quality metric

Cite this