Learning degradation priors for reliable no-reference image quality assessment

Hua Zhang, Zhuonan Shen, Bolun Zheng, Quan Chen, Dingguo Yu, Yiru Chen, Chenggang Yan

Abstract: Highlights•We propose a novel architecture involving degradation priors and semantic features for NR-IQA.•A multi-task learning framework is proposed for NR-IQA, intergating semantic features and frequency domain degradation features.•We collect a new dataset namely ReD-1K, which consists of 537 pairs of degraded and non-degraded real images.