Perceptual Quality Assessment of Omnidirectional Audio-visual Signals
This work addresses the lack of audio-visual quality assessment for omnidirectional videos, which is important for service-providers to improve user experience in fields like medical and education, but it is incremental as it builds on existing single-mode models.
The authors tackled the problem of assessing the quality of omnidirectional audio-visual signals by establishing a large-scale dataset with 375 distorted sequences and corresponding perceptual scores, and they validated multimodal fusion methods that provide a new benchmark for omnidirectional quality of experience evaluation.
Omnidirectional videos (ODVs) play an increasingly important role in the application fields of medical, education, advertising, tourism, etc. Assessing the quality of ODVs is significant for service-providers to improve the user's Quality of Experience (QoE). However, most existing quality assessment studies for ODVs only focus on the visual distortions of videos, while ignoring that the overall QoE also depends on the accompanying audio signals. In this paper, we first establish a large-scale audio-visual quality assessment dataset for omnidirectional videos, which includes 375 distorted omnidirectional audio-visual (A/V) sequences generated from 15 high-quality pristine omnidirectional A/V contents, and the corresponding perceptual audio-visual quality scores. Then, we design three baseline methods for full-reference omnidirectional audio-visual quality assessment (OAVQA), which combine existing state-of-the-art single-mode audio and video QA models via multimodal fusion strategies. We validate the effectiveness of the A/V multimodal fusion method for OAVQA on our dataset, which provides a new benchmark for omnidirectional QoE evaluation. Our dataset is available at https://github.com/iamazxl/OAVQA.