A Neural Network Model of Spatial Distortion Sensitivity for Video Quality Estimation

Soren Becker; Klaus Robert Muller; Thomas Wiegand; Sebastian Bosse

doi:10.1109/MLSP.2019.8918899

A Neural Network Model of Spatial Distortion Sensitivity for Video Quality Estimation

Soren Becker, Klaus Robert Muller, Thomas Wiegand, Sebastian Bosse

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

Accurate estimation of visual quality as perceived by humans is crucial for modern multimedia systems and, given the evident ease for humans, a surprisingly difficult task for computers. Complexity considerations as imperative for real-time applications render this problem even more challenging. This paper studies the application of a neural network-based spatial model of distortion sensitivity to the quality prediction of spatio-temporal videos. We propose a simple yet effective adaptation of the loss function to cope with saturation effects in human quality ratings. This adaptation drastically decreases the number of iterations necessary for training networks to replicate psychophysical human responses. Our experimental results show significantly improved prediction performance of the spatio-temporal PSNR when compensated for spatial distortion sensitivity while maintaining the advantage of low complexity.

Original language	English
Title of host publication	2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019
Publisher	IEEE Computer Society
ISBN (Electronic)	9781728108247
DOIs	https://doi.org/10.1109/MLSP.2019.8918899
Publication status	Published - 2019 Oct
Event	29th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2019 - Pittsburgh, United States Duration: 2019 Oct 13 → 2019 Oct 16

Publication series

Name	IEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume	2019-October
ISSN (Print)	2161-0363
ISSN (Electronic)	2161-0371

Conference

Conference	29th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2019
Country/Territory	United States
City	Pittsburgh
Period	19/10/13 → 19/10/16

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Visual perception
distortion sensitivity
neural network
video compression
video quality

ASJC Scopus subject areas

Human-Computer Interaction
Signal Processing

Access to Document

10.1109/MLSP.2019.8918899

Cite this

Becker, S., Muller, K. R., Wiegand, T., & Bosse, S. (2019). A Neural Network Model of Spatial Distortion Sensitivity for Video Quality Estimation. In 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019 Article 8918899 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2019-October). IEEE Computer Society. https://doi.org/10.1109/MLSP.2019.8918899

A Neural Network Model of Spatial Distortion Sensitivity for Video Quality Estimation. / Becker, Soren; Muller, Klaus Robert; Wiegand, Thomas et al.
2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019. IEEE Computer Society, 2019. 8918899 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2019-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Becker, S, Muller, KR, Wiegand, T & Bosse, S 2019, A Neural Network Model of Spatial Distortion Sensitivity for Video Quality Estimation. in 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019., 8918899, IEEE International Workshop on Machine Learning for Signal Processing, MLSP, vol. 2019-October, IEEE Computer Society, 29th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2019, Pittsburgh, United States, 19/10/13. https://doi.org/10.1109/MLSP.2019.8918899

Becker S, Muller KR, Wiegand T, Bosse S. A Neural Network Model of Spatial Distortion Sensitivity for Video Quality Estimation. In 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019. IEEE Computer Society. 2019. 8918899. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP). doi: 10.1109/MLSP.2019.8918899

@inproceedings{01003ffbe4e24b3fbaa2ad1b581abf8f,

title = "A Neural Network Model of Spatial Distortion Sensitivity for Video Quality Estimation",

abstract = "Accurate estimation of visual quality as perceived by humans is crucial for modern multimedia systems and, given the evident ease for humans, a surprisingly difficult task for computers. Complexity considerations as imperative for real-time applications render this problem even more challenging. This paper studies the application of a neural network-based spatial model of distortion sensitivity to the quality prediction of spatio-temporal videos. We propose a simple yet effective adaptation of the loss function to cope with saturation effects in human quality ratings. This adaptation drastically decreases the number of iterations necessary for training networks to replicate psychophysical human responses. Our experimental results show significantly improved prediction performance of the spatio-temporal PSNR when compensated for spatial distortion sensitivity while maintaining the advantage of low complexity.",

keywords = "Visual perception, distortion sensitivity, neural network, video compression, video quality",

author = "Soren Becker and Muller, {Klaus Robert} and Thomas Wiegand and Sebastian Bosse",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 29th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2019 ; Conference date: 13-10-2019 Through 16-10-2019",

year = "2019",

month = oct,

doi = "10.1109/MLSP.2019.8918899",

language = "English",

series = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

publisher = "IEEE Computer Society",

booktitle = "2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019",

}

TY - GEN

T1 - A Neural Network Model of Spatial Distortion Sensitivity for Video Quality Estimation

AU - Becker, Soren

AU - Muller, Klaus Robert

AU - Wiegand, Thomas

AU - Bosse, Sebastian

PY - 2019/10

Y1 - 2019/10

N2 - Accurate estimation of visual quality as perceived by humans is crucial for modern multimedia systems and, given the evident ease for humans, a surprisingly difficult task for computers. Complexity considerations as imperative for real-time applications render this problem even more challenging. This paper studies the application of a neural network-based spatial model of distortion sensitivity to the quality prediction of spatio-temporal videos. We propose a simple yet effective adaptation of the loss function to cope with saturation effects in human quality ratings. This adaptation drastically decreases the number of iterations necessary for training networks to replicate psychophysical human responses. Our experimental results show significantly improved prediction performance of the spatio-temporal PSNR when compensated for spatial distortion sensitivity while maintaining the advantage of low complexity.

AB - Accurate estimation of visual quality as perceived by humans is crucial for modern multimedia systems and, given the evident ease for humans, a surprisingly difficult task for computers. Complexity considerations as imperative for real-time applications render this problem even more challenging. This paper studies the application of a neural network-based spatial model of distortion sensitivity to the quality prediction of spatio-temporal videos. We propose a simple yet effective adaptation of the loss function to cope with saturation effects in human quality ratings. This adaptation drastically decreases the number of iterations necessary for training networks to replicate psychophysical human responses. Our experimental results show significantly improved prediction performance of the spatio-temporal PSNR when compensated for spatial distortion sensitivity while maintaining the advantage of low complexity.

KW - Visual perception

KW - distortion sensitivity

KW - neural network

KW - video compression

KW - video quality

UR - http://www.scopus.com/inward/record.url?scp=85077717964&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2019.8918899

DO - 10.1109/MLSP.2019.8918899

M3 - Conference contribution

AN - SCOPUS:85077717964

T3 - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

BT - 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019

PB - IEEE Computer Society

T2 - 29th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2019

Y2 - 13 October 2019 through 16 October 2019

ER -

A Neural Network Model of Spatial Distortion Sensitivity for Video Quality Estimation

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this