Perceptual Quality Assessment of Omnidirectional Audio-visual Signals

TL;DR

This paper introduces a large-scale dataset and baseline methods for assessing the perceptual quality of omnidirectional audio-visual signals, emphasizing the importance of combined audio-visual evaluation for improved QoE.

Contribution

The paper presents the first large-scale audio-visual quality assessment dataset for omnidirectional videos and proposes multimodal fusion methods for full-reference quality evaluation.

Findings

Multimodal fusion improves quality assessment accuracy.

The dataset enables benchmarking of audio-visual QoE.

Baseline methods outperform single-modality assessments.

Abstract

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.