XGC-VQA: A unified video quality assessment model for User, Professionally, and Occupationally-Generated Content

TL;DR

This paper introduces XGC-VQA, a unified real-time video quality assessment model tailored for user, professional, and occupational content, utilizing non-uniform sampling and downsampling to optimize perceptual quality evaluation.

Contribution

It presents a novel unified VQA model that efficiently assesses diverse content types with real-time performance using innovative sampling and downsampling techniques.

Findings

Achieves median correlation of 0.7 in quality assessment.

Maintains computation time below 5 seconds for all content types.

Effectively optimizes communication experience across content categories.

Abstract

With the rapid growth of Internet video data amounts and types, a unified Video Quality Assessment (VQA) is needed to inspire video communication with perceptual quality. To meet the real-time and universal requirements in providing such inspiration, this study proposes a VQA model from a classification of User Generated Content (UGC), Professionally Generated Content (PGC), and Occupationally Generated Content (OGC). In the time domain, this study utilizes non-uniform sampling, as each content type has varying temporal importance based on its perceptual quality. In the spatial domain, centralized downsampling is performed before the VQA process by utilizing a patch splicing/sampling mechanism to lower complexity for real-time assessment. The experimental results demonstrate that the proposed method achieves a median correlation of $0.7$ while limiting the computation time below 5s for three content types, which ensures that the communication experience of UGC, PGC, and OGC can be optimized altogether.