SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment
This work addresses the need for reliable image quality assessment to verify compression algorithms and guide optimization, representing an incremental improvement in domain-specific IQA.
The paper tackles the problem of assessing perceptual quality for compressed images by proposing SwinIQA, a full-reference metric that uses a learned Swin distance space, achieving higher consistency with human judgment compared to traditional and learning-based methods on CLIC datasets.
Image compression has raised widespread interest recently due to its significant importance for multimedia storage and transmission. Meanwhile, a reliable image quality assessment (IQA) for compressed images can not only help to verify the performance of various compression algorithms but also help to guide the compression optimization in turn. In this paper, we design a full-reference image quality assessment metric SwinIQA to measure the perceptual quality of compressed images in a learned Swin distance space. It is known that the compression artifacts are usually non-uniformly distributed with diverse distortion types and degrees. To warp the compressed images into the shared representation space while maintaining the complex distortion information, we extract the hierarchical feature representations from each stage of the Swin Transformer. Besides, we utilize cross attention operation to map the extracted feature representations into a learned Swin distance space. Experimental results show that the proposed metric achieves higher consistency with human's perceptual judgment compared with both traditional methods and learning-based methods on CLIC datasets.