Assessing Visual Quality of Omnidirectional Videos

TL;DR

This paper introduces new subjective and objective methods for assessing the visual quality of omnidirectional videos, supported by a novel database and analysis of viewing behaviors, improving upon existing VQA techniques.

Contribution

The paper presents a new database of viewing directions, and develops both subjective and objective VQA methods tailored for omnidirectional videos, considering human perception and viewing patterns.

Findings

High consistency in viewing directions across subjects

Objective VQA methods outperform existing techniques

Proposed methods align well with human subjective assessments

Abstract

In contrast with traditional video, omnidirectional video enables spherical viewing direction with support for head-mounted displays, providing an interactive and immersive experience. Unfortunately, to the best of our knowledge, there are few visual quality assessment (VQA) methods, either subjective or objective, for omnidirectional video coding. This paper proposes both subjective and objective methods for assessing quality loss in encoding omnidirectional video. Specifically, we first present a new database, which includes the viewing direction data from several subjects watching omnidirectional video sequences. Then, from our database, we find a high consistency in viewing directions across different subjects. The viewing directions are normally distributed in the center of the front regions, but they sometimes fall into other regions, related to video content. Given this finding, we present a subjective VQA method for measuring difference mean opinion score (DMOS) of the whole and regional omnidirectional video, in terms of overall DMOS (O-DMOS) and vectorized DMOS (V-DMOS), respectively. Moreover, we propose two objective VQA methods for encoded omnidirectional video, in light of human perception characteristics of omnidirectional video. One method weighs the distortion of pixels with regard to their distances to the center of front regions, which considers human preference in a panorama. The other method predicts viewing directions according to video content, and then the predicted viewing directions are leveraged to allocate weights to the distortion of each pixel in our objective VQA method. Finally, our experimental results verify that both the subjective and objective methods proposed in this paper advance state-of-the-art VQA for omnidirectional video.