Comparison Drives Preference: Reference-Aware Modeling for AI-Generated Video Quality Assessment

TL;DR

This paper introduces RefVQA, a reference-aware method for AI-generated video quality assessment that leverages relationships among videos to improve evaluation accuracy and better align with human perception.

Contribution

It formulates AIGC-VQA as a reference-aware problem and proposes a graph-guided approach that outperforms existing methods across multiple datasets.

Findings

RefVQA outperforms state-of-the-art methods in quality assessment.

The reference-aware approach generalizes well across datasets.

Graph-guided difference aggregation improves evaluation accuracy.

Abstract

The rapid advancement of generative models has led to a growing volume of AI-generated videos, making the automatic quality assessment of such videos increasingly important. Existing AI-generated content video quality assessment (AIGC-VQA) methods typically estimate visual quality by analyzing each video independently, ignoring potential relationships among videos. In this work, we revisit AIGC-VQA from an inter-video perspective and formulate it as a reference-aware evaluation problem. Through this formulation, quality assessment is guided not only by intrinsic video characteristics but also by comparisons with related videos, which is more consistent with human perception. To validate its effectiveness, we propose Reference-aware Video Quality Assessment (RefVQA), which utilizes a query-centered reference graph to organize semantically related samples and performs graph-guided difference aggregation from the reference nodes to the query node. Experiments on existing datasets demonstrate that our proposed RefVQA outperforms state-of-the-art methods across multiple quality dimensions, with strong generalization ability validated by cross-dataset evaluation. These results highlight the effectiveness of the proposed reference-based formulation and suggest its potential to advance AIGC-VQA.