FUNQUE: Fusion of Unified Quality Evaluators

TL;DR

FUNQUE introduces a unified quality evaluation framework that combines multiple models in a common domain, improving accuracy and efficiency in video quality assessment.

Contribution

It unifies diverse quality models in a shared transform domain and proposes a fusion method that enhances prediction accuracy and reduces computational costs.

Findings

FUNQUE outperforms existing models in correlation with subjective scores.

It achieves higher efficiency through computation sharing.

Demonstrates significant improvements over state-of-the-art methods.

Abstract

Fusion-based quality assessment has emerged as a powerful method for developing high-performance quality models from quality models that individually achieve lower performances. A prominent example of such an algorithm is VMAF, which has been widely adopted as an industry standard for video quality prediction along with SSIM. In addition to advancing the state-of-the-art, it is imperative to alleviate the computational burden presented by the use of a heterogeneous set of quality models. In this paper, we unify "atom" quality models by computing them on a common transform domain that accounts for the Human Visual System, and we propose FUNQUE, a quality model that fuses unified quality evaluators. We demonstrate that in comparison to the state-of-the-art, FUNQUE offers significant improvements in both correlation against subjective scores and efficiency, due to computation sharing.