Cross-IQA: Unsupervised Learning for Image Quality Assessment

TL;DR

Cross-IQA introduces an unsupervised vision transformer-based method for image quality assessment that learns from unlabeled data and achieves state-of-the-art results in detecting low-frequency degradations.

Contribution

It proposes a novel unsupervised learning approach using ViT and a synthesized image reconstruction task for no-reference image quality assessment.

Findings

Achieves state-of-the-art performance on low-frequency degradation detection.

Effectively learns image quality features from unlabeled data.

Outperforms classical full-reference and no-reference IQA methods.

Abstract

Automatic perception of image quality is a challenging problem that impacts billions of Internet and social media users daily. To advance research in this field, we propose a no-reference image quality assessment (NR-IQA) method termed Cross-IQA based on vision transformer(ViT) model. The proposed Cross-IQA method can learn image quality features from unlabeled image data. We construct the pretext task of synthesized image reconstruction to unsupervised extract the image quality information based ViT block. The pretrained encoder of Cross-IQA is used to fine-tune a linear regression model for score prediction. Experimental results show that Cross-IQA can achieve state-of-the-art performance in assessing the low-frequency degradation information (e.g., color change, blurring, etc.) of images compared with the classical full-reference IQA and NR-IQA under the same datasets.