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

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 paper, 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, i.e., 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. Our code is available at https://github.com/xinyouu/PFIQA.

I. Introduction

Image super-resolution (SR) technology aims to produce more detailed high-resolution (HR) images from the given low-resolution (LR) images. It has been widely used in various fields, such as security and surveillance [1], medical imaging [2], and remote sensing imaging [3], [4]. Given the remarkable advancements in recent research on SR algorithms, including blind SR [5], [6], [7], lightweight SR [8], [9], [10], arbitrary scale SR [11], and multimodal SR [12], [13], it has become imperative to evaluate the quality of the generated SR images. This evaluation is crucial for facilitating comparative analysis of reconstruction performance across various SR models and guiding the development of SR algorithms.