ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment

TL;DR

ReLaX-VQA is a new no-reference video quality assessment model that uses fragment selection and layer stacking techniques to effectively evaluate diverse user-generated videos without needing original references.

Contribution

The paper introduces ReLaX-VQA, a novel NR-VQA model that combines spatio-temporal fragment selection with deep feature layer stacking to improve quality assessment accuracy.

Findings

Outperforms existing NR-VQA methods on four datasets.

Achieves an average SRCC of 0.8658 and PLCC of 0.8873.

Demonstrates robustness across diverse UGC content.

Abstract

With the rapid growth of User-Generated Content (UGC) exchanged between users and sharing platforms, the need for video quality assessment in the wild is increasingly evident. UGC is typically acquired using consumer devices and undergoes multiple rounds of compression (transcoding) before reaching the end user. Therefore, traditional quality metrics that employ the original content as a reference are not suitable. In this paper, we propose ReLaX-VQA, a novel No-Reference Video Quality Assessment (NR-VQA) model that aims to address the challenges of evaluating the quality of diverse video content without reference to the original uncompressed videos. ReLaX-VQA uses frame differences to select spatio-temporal fragments intelligently together with different expressions of spatial features associated with the sampled frames. These are then used to better capture spatial and temporal variabilities in the quality of neighbouring frames. Furthermore, the model enhances abstraction by employing layer-stacking techniques in deep neural network features from Residual Networks and Vision Transformers. Extensive testing across four UGC datasets demonstrates that ReLaX-VQA consistently outperforms existing NR-VQA methods, achieving an average SRCC of 0.8658 and PLCC of 0.8873. Open-source code and trained models that will facilitate further research and applications of NR-VQA can be found at https://github.com/xinyiW915/ReLaX-VQA.