SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment

TL;DR

SwinIQA introduces a learned Swin distance-based full-reference image quality assessment metric that effectively measures perceptual quality of compressed images, outperforming traditional and existing learning-based methods.

Contribution

The paper proposes a novel SwinIQA metric that leverages hierarchical Swin Transformer features and cross attention to accurately assess compressed image quality.

Findings

Achieves higher correlation with human judgment than traditional methods.

Outperforms existing learning-based IQA metrics on CLIC datasets.

Effectively captures complex distortion information in compressed images.

Abstract

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.