Visual quality assessment for interpolated slow-motion videos based on a novel database

Hui Men, Vlad Hosu, Hanhe Lin, Andrés Bruhn, Dietmar Saupe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Professional video editing tools can generate slow-motion video by interpolating frames from video recorded at a standard frame rate. Thereby the perceptual quality of such interpolated slow-motion videos strongly depends on the underlying interpolation techniques. We built a novel benchmark database that is specifically tailored for interpolated slow-motion videos (KoSMo-1k). It consists of 1,350 interpolated video sequences, from 30 different content sources, along with their subjective quality ratings from up to ten subjective comparisons per video pair. Moreover, we evaluated the performance of twelve existing full-reference (FR) image/video quality assessment (I/VQA) methods on the benchmark. In this way, we are able to show that specifically tailored quality assessment methods for interpolated slow-motion videos are needed, since the evaluated methods - despite their good performance on real-time video databases - do not give satisfying results when it comes to frame interpolation.

Original languageEnglish
Title of host publication2020 12th International Conference on Quality of Multimedia Experience (QoMEX 2020)
PublisherIEEE
Number of pages6
ISBN (Electronic)978-1-7281-5965-2
ISBN (Print)978-1-7281-5966-9
DOIs
Publication statusPublished - 23 Jun 2020
Event12th International Conference on Quality of Multimedia Experience, QoMEX 2020 - Athlone, Ireland
Duration: 26 May 202028 May 2020

Publication series

Name2020 12th International Conference on Quality of Multimedia Experience, QoMEX 2020
PublisherIEEE
ISSN (Print)2372-7179
ISSN (Electronic)2472-7814

Conference

Conference12th International Conference on Quality of Multimedia Experience, QoMEX 2020
Country/TerritoryIreland
CityAthlone
Period26/05/2028/05/20

Keywords

  • frame interpolation
  • optical flow
  • slow motion
  • visual quality assessment

Fingerprint

Dive into the research topics of 'Visual quality assessment for interpolated slow-motion videos based on a novel database'. Together they form a unique fingerprint.

Cite this