FUNQUE: Fusion of Unified Quality Evaluators
This work addresses computational efficiency for video quality prediction, which is important for industry applications, but it is incremental as it builds on existing fusion methods like VMAF.
The paper tackles the problem of computational burden in fusion-based quality assessment by unifying 'atom' quality models on a common transform domain, resulting in FUNQUE, which shows significant improvements in correlation against subjective scores and efficiency compared to the state-of-the-art.
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.