Priorformer: A UGC-VQA Method with content and distortion priors

TL;DR

PriorFormer is a novel UGC video quality assessment method that uses content and distortion priors to improve adaptability and performance across diverse content and degradations, achieving state-of-the-art results.

Contribution

The paper introduces a new prior-augmented vision transformer that incorporates content and distortion priors for improved blind video quality assessment of UGC.

Findings

Achieves state-of-the-art performance on three UGC VQA datasets.

Effectively models diverse content and distortions in UGC videos.

Utilizes pre-trained feature extractors for content and distortion embeddings.

Abstract

User Generated Content (UGC) videos are susceptible to complicated and variant degradations and contents, which prevents the existing blind video quality assessment (BVQA) models from good performance since the lack of the adapability of distortions and contents. To mitigate this, we propose a novel prior-augmented perceptual vision transformer (PriorFormer) for the BVQA of UGC, which boots its adaptability and representation capability for divergent contents and distortions. Concretely, we introduce two powerful priors, i.e., the content and distortion priors, by extracting the content and distortion embeddings from two pre-trained feature extractors. Then we adopt these two powerful embeddings as the adaptive prior tokens, which are transferred to the vision transformer backbone jointly with implicit quality features. Based on the above strategy, the proposed PriorFormer achieves state-of-the-art performance on three public UGC VQA datasets including KoNViD-1K, LIVE-VQC and YouTube-UGC.