VR Video Quality in the Wild

Investigating how people perceive virtual reality videos in the wild (i.e., those captured by everyday users) is a crucial and challenging task in VR-related applications due to complex authentic distortions localized in space and time. Existing panoramic video databases only consider synthetic distortions, assume fixed viewing conditions, and are limited in size. To overcome these shortcomings, we construct the VR Video Quality in the Wild (VRVQW) database, which is one of the first of its kind, and contains 502 user-generated videos with diverse content and distortion characteristics. Based on VRVQW, we conduct a formal psychophysical experiment to record the scanpaths and perceived quality scores from 139 participants under two different viewing conditions. We provide a thorough sta- tistical analysis of the recorded data, observing significant impact of viewing conditions on both human scanpaths and perceived quality. Moreover, we develop an objective quality assessment model for VR videos based on pseudocylindrical representation and convolution. Results on the proposed VRVQW show that our method is superior to existing video quality assessment models, only underperforming viewport-based models that otherwise rely on human scanpaths for projection. We have made the database and code available at https://github.com/limuhit/VR-Video-Quality-in-the-Wild.

探究普通用户日常录制的野外场景虚拟现实（Virtual Reality, VR）视频的主观感知，是VR相关应用领域中一项兼具重要性与挑战性的任务——这是因为此类视频存在时空分布的复杂真实失真。现有全景视频数据库仅考虑合成失真，且假设观看条件固定，样本规模亦较为有限。为克服上述局限，我们构建了野外虚拟现实视频质量（VR Video Quality in the Wild, VRVQW）数据库，该库是同类首批数据集之一，包含502条用户生成的、内容与失真特征均具多样性的视频。基于VRVQW数据库，我们开展了正式的心理物理学实验：在两种不同的观看条件下，记录了139名受试者的眼动扫描路径（scanpaths）与主观质量评分。我们对采集到的实验数据开展了全面的统计分析，发现观看条件对人类眼动扫描路径与主观感知质量均存在显著影响。此外，我们基于伪圆柱投影表示与卷积操作，构建了一款VR视频客观质量评估模型。在自建的VRVQW数据库上的实验结果表明，所提方法的性能优于现有主流视频质量评估模型，仅略逊于依赖人类眼动扫描路径进行投影的基于视口（viewport）的模型。本数据库与相关代码已开源至：https://github.com/limuhit/VR-Video-Quality-in-the-Wild。

搜集汇总

背景与挑战

背景概述

VR Video Quality in the Wild（VRVQW）是一个专注于研究自然环境中用户生成虚拟现实视频质量感知的数据集，包含502个多样化的视频，并通过139名参与者的实验收集了扫描路径和质量评分。该数据集首次解决了真实失真和可变观看条件的问题，并提供了基于伪圆柱表示的客观质量评估模型，公开了数据库和代码以促进相关研究。