DIVA-VQA: Detecting Inter-frame Variations in UGC Video Quality

TL;DR

This paper introduces DIVA-VQA, a no-reference video quality assessment model that analyzes inter-frame variations in user-generated videos to accurately predict quality without a reference, achieving top performance with low complexity.

Contribution

The paper presents a novel NR-VQA model leveraging inter-frame differences and spatio-temporal fragmentation, improving accuracy and efficiency over existing methods.

Findings

Achieved top 2 ranking on five UGC datasets in correlation metrics.

Outperformed state-of-the-art models in accuracy while maintaining low runtime complexity.

Demonstrated effectiveness of inter-frame variation analysis in perceptual video quality assessment.

Abstract

The rapid growth of user-generated (video) content (UGC) has driven increased demand for research on no-reference (NR) perceptual video quality assessment (VQA). NR-VQA is a key component for large-scale video quality monitoring in social media and streaming applications where a pristine reference is not available. This paper proposes a novel NR-VQA model based on spatio-temporal fragmentation driven by inter-frame variations. By leveraging these inter-frame differences, the model progressively analyses quality-sensitive regions at multiple levels: frames, patches, and fragmented frames. It integrates frames, fragmented residuals, and fragmented frames aligned with residuals to effectively capture global and local information. The model extracts both 2D and 3D features in order to characterize these spatio-temporal variations. Experiments conducted on five UGC datasets and against state-of-the-art models ranked our proposed method among the top 2 in terms of average rank correlation (DIVA-VQA-L: 0.898 and DIVA-VQA-B: 0.886). The improved performance is offered at a low runtime complexity, with DIVA-VQA-B ranked top and DIVA-VQA-L third on average compared to the fastest existing NR-VQA method. Code and models are publicly available at: https://github.com/xinyiW915/DIVA-VQA.