Perception- and Fidelity-aware Reduced-Reference Super-Resolution Image Quality Assessment

TL;DR

This paper introduces PFIQA, a dual-branch reduced-reference network that evaluates both perceptual quality and fidelity of super-resolution images using limited reference information, outperforming existing methods.

Contribution

The paper proposes a novel dual-branch network leveraging Vision Transformer and ResNet for comprehensive SR image quality assessment without high-resolution references.

Findings

PFIQA outperforms state-of-the-art models on SR-IQA benchmarks.

PFIQA effectively assesses real-world SR images.

The dual-branch design aligns with human visual perception.

Abstract

With the advent of image super-resolution (SR) algorithms, how to evaluate the quality of generated SR images has become an urgent task. Although full-reference methods perform well in SR image quality assessment (SR-IQA), their reliance on high-resolution (HR) images limits their practical applicability. Leveraging available reconstruction information as much as possible for SR-IQA, such as low-resolution (LR) images and the scale factors, is a promising way to enhance assessment performance for SR-IQA without HR for reference. In this letter, we attempt to evaluate the perceptual quality and reconstruction fidelity of SR images considering LR images and scale factors. Specifically, we propose a novel dual-branch reduced-reference SR-IQA network, \ie, Perception- and Fidelity-aware SR-IQA (PFIQA). The perception-aware branch evaluates the perceptual quality of SR images by leveraging the merits of global modeling of Vision Transformer (ViT) and local relation of ResNet, and incorporating the scale factor to enable comprehensive visual perception. Meanwhile, the fidelity-aware branch assesses the reconstruction fidelity between LR and SR images through their visual perception. The combination of the two branches substantially aligns with the human visual system, enabling a comprehensive SR image evaluation. Experimental results indicate that our PFIQA outperforms current state-of-the-art models across three widely-used SR-IQA benchmarks. Notably, PFIQA excels in assessing the quality of real-world SR images.