Dual-Representation Interaction Driven Image Quality Assessment with Restoration Assistance

TL;DR

This paper introduces a dual-representation interaction method for no-reference image quality assessment that effectively models degradation and quality factors, improving performance on synthetic and real-world distorted images.

Contribution

The paper proposes a novel dual-representation interaction approach with degradation and quality vectors, and a semantic loss to enhance feature interaction for better IQA performance.

Findings

Outperforms existing models on synthetic datasets

Achieves superior results on real-world datasets

Effectively models degradation factors for improved assessment

Abstract

No-Reference Image Quality Assessment for distorted images has always been a challenging problem due to image content variance and distortion diversity. Previous IQA models mostly encode explicit single-quality features of synthetic images to obtain quality-aware representations for quality score prediction. However, performance decreases when facing real-world distortion and restored images from restoration models. The reason is that they do not consider the degradation factors of the low-quality images adequately. To address this issue, we first introduce the DRI method to obtain degradation vectors and quality vectors of images, which separately model the degradation and quality information of low-quality images. After that, we add the restoration network to provide the MOS score predictor with degradation information. Then, we design the Representation-based Semantic Loss (RS Loss) to assist in enhancing effective interaction between representations. Extensive experimental results demonstrate that the proposed method performs favorably against existing state-of-the-art models on both synthetic and real-world datasets.