Cross-IQA: Unsupervised Learning for Image Quality Assessment
This addresses image quality perception for billions of Internet and social media users, but it is incremental as it builds on existing unsupervised and transformer-based approaches.
The paper tackles the problem of automatic image quality assessment by proposing Cross-IQA, an unsupervised no-reference method based on vision transformers, which achieves state-of-the-art performance in assessing low-frequency degradations like color change and blurring.
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.