TY - GEN
T1 - Visual quality assessment for interpolated slow-motion videos based on a novel database
AU - Men, Hui
AU - Hosu, Vlad
AU - Lin, Hanhe
AU - Bruhn, Andrés
AU - Saupe, Dietmar
N1 - Funding Information:
Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – Project-ID 251654672 – TRR 161 (Project A05 and B04).
Publisher Copyright:
© 2020 IEEE.
PY - 2020/6/23
Y1 - 2020/6/23
N2 - 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.
AB - 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.
KW - frame interpolation
KW - optical flow
KW - slow motion
KW - visual quality assessment
UR - http://www.scopus.com/inward/record.url?scp=85087660971&partnerID=8YFLogxK
U2 - 10.1109/QoMEX48832.2020.9123096
DO - 10.1109/QoMEX48832.2020.9123096
M3 - Conference contribution
AN - SCOPUS:85087660971
SN - 978-1-7281-5966-9
T3 - 2020 12th International Conference on Quality of Multimedia Experience, QoMEX 2020
BT - 2020 12th International Conference on Quality of Multimedia Experience (QoMEX 2020)
PB - IEEE
T2 - 12th International Conference on Quality of Multimedia Experience, QoMEX 2020
Y2 - 26 May 2020 through 28 May 2020
ER -