No-Reference Image Quality Assessment with Global-Local Progressive Integration and Semantic-Aligned Quality Transfer

TL;DR

This paper introduces a novel no-reference image quality assessment model that combines global and local features through progressive integration and semantic-aligned quality transfer, achieving improved accuracy and generalization.

Contribution

It presents a dual-measurement framework with a progressive feature integration scheme and a semantic-aligned quality transfer method, enhancing no-reference image quality assessment performance.

Findings

Achieved over 5% improvement in SROCC on cross-dataset tests.

Demonstrated effectiveness of semantic-aligned quality transfer in boosting performance.

Outperformed existing methods in both synthetic and authentic image quality assessments.

Abstract

Accurate measurement of image quality without reference signals remains a fundamental challenge in low-level visual perception applications. In this paper, we propose a global-local progressive integration model that addresses this challenge through three key contributions: 1) We develop a dual-measurement framework that combines vision Transformer (ViT)-based global feature extractor and convolutional neural networks (CNNs)-based local feature extractor to comprehensively capture and quantify image distortion characteristics at different granularities. 2) We propose a progressive feature integration scheme that utilizes multi-scale kernel configurations to align global and local features, and progressively aggregates them via an interactive stack of channel-wise self-attention and spatial interaction modules for multi-grained quality-aware representations. 3) We introduce a semantic-aligned quality transfer method that extends the training data by automatically labeling the quality scores of diverse image content with subjective opinion scores. Experimental results demonstrate that our model yields 5.04% and 5.40% improvements in Spearman's rank-order correlation coefficient (SROCC) for cross-authentic and cross-synthetic dataset generalization tests, respectively. Furthermore, the proposed semantic-aligned quality transfer further yields 2.26% and 13.23% performance gains in evaluations on single-synthetic and cross-synthetic datasets.