FGSVQA: Frequency-Guided Short-form Video Quality Assessment

TL;DR

This paper introduces FGSVQA, an end-to-end framework for assessing short-form video quality using frequency-guided features and a dense visual encoder, achieving high accuracy and efficiency.

Contribution

The paper presents a novel frequency-guided, structure-aware VQA framework that effectively handles complex distortions in user-generated short videos.

Findings

Achieves SRCC of 0.736 and PLCC of 0.787 on short-form video datasets.

Employs a frequency domain prior to improve artifact and structure awareness.

Maintains efficient inference runtime while delivering accurate quality predictions.

Abstract

Short-form video poses new challenges to the quality assessment of user-generated content (UGC) due to its complex generation pipeline, rapid content variation, and mixed distortions. To address this challenge, we propose an end-to-end video quality assessment (VQA) framework that employs a dense visual encoder based on CLIP, and incorporates compression priors derived from the frequency domain to generate artifact- and structure-aware weight maps for feature aggregation. By explicitly decomposing artifact, structure, and original visual feature branches and adaptively fusing them over time through a learned gating module, the proposed method achieves accurate and efficient quality prediction. Experimental results show that our method achieves strong performance on short-form video datasets in terms of average rank and linear correlation (SRCC: 0.736, PLCC: 0.787), while maintaining efficient inference runtime. The code and additional results are available at: https://github.com/xinyiW915/FGSVQA.