Share Email Print

Proceedings Paper

Deep learning and video quality analysis
Author(s): P. Topiwala; M. Krishnan; W. Dai
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

For more than 30 years, the video coding industry has been using mean-squared error-based PSNR as a measure of video quality, despite evidence of its inadequacy. Moreover, in the encoder, SAD is used instead of MSE to save multiplications. We quantify how these measures are inadequately correlated to subjective scores and obtain new measures that correlate much better. We focus on the problem of full-reference assessment of video degraded only by coding and scaling errors, such as experienced by streaming services, and put aside issues of transmission, such as timing jitters, rebufferings, etc. We begin with the Video Multi- Assessment Fusion (VMAF) algorithm introduced by Netflix. Results with up to 97% correlation accuracy to subjective scores are reported on two Netflix datasets, using a neural network model.

Paper Details

Date Published: 6 September 2019
PDF: 9 pages
Proc. SPIE 11137, Applications of Digital Image Processing XLII, 111370T (6 September 2019); doi: 10.1117/12.2530557
Show Author Affiliations
P. Topiwala, FastVDO Inc. (United States)
M. Krishnan, FastVDO Inc. (United States)
W. Dai, FastVDO Inc. (United States)

Published in SPIE Proceedings Vol. 11137:
Applications of Digital Image Processing XLII
Andrew G. Tescher; Touradj Ebrahimi, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?