Perceptual evaluation on audio-visual dataset of 360 content

Randy Fela (1) , Andreas Pastor (2, 3) , Patrick Le Callet (3, 2) , Nick Zacharov (4) , Toinon Vigier (2, 3) , Soren Forchhammer (1)

1 DTU - Danmarks Tekniske Universitet = Technical University of Denmark
2 LS2N - équipe IPI - Image Perception Interaction
3 LS2N - Laboratoire des Sciences du Numérique de Nantes
4 Meta AI Research [Paris]

To open up new possibilities to assess the multimodal perceptual quality of omnidirectional media formats, we proposed a novel open source 360 audiovisual (AV) quality dataset. The dataset consists of high-quality 360 video clips in equirectangular (ERP) format and higher-order ambisonic (4 th order) along with the subjective scores. Three subjective quality experiments were conducted for audio, video, and AV with the procedures detailed in this paper. Using the data from subjective tests, we demonstrated that this dataset can be used to quantify perceived audio, video, and audiovisual quality. The diversity and discriminability of subjective scores were also analyzed. Finally, we investigated how our dataset correlates with various objective quality metrics of audio and video. Evidence from the results of this study implies that the proposed dataset can benefit future studies on multimodal quality evaluation of 360 content.

Mots clés: omnidirectional media format; audiovisual dataset; 360 video; ambisonic; quality evaluation

Domaines: Informatique [cs]

Randy Fela, Andreas Pastor, Patrick Le Callet, Nick Zacharov, Toinon Vigier, et al.. Perceptual evaluation on audio-visual dataset of 360 content. 2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), Jul 2022, Taipei City, Taiwan. pp.1-6, ⟨10.1109/ICMEW56448.2022.9859426⟩. ⟨hal-03850338⟩