Deep Feature Statistics Mapping for Generalized Screen Content Image Quality Assessment

TL;DR

This paper introduces a novel deep learning-based method for no-reference screen content image quality assessment by learning the unique statistical regularities of SCIs, which are different from natural images, leading to improved accuracy and generalization.

Contribution

The paper pioneers the learning of statistical regularities specific to SCIs for quality assessment, filling a gap in no-reference image quality evaluation methods.

Findings

The proposed DFSS-IQA model outperforms existing NR-IQA models.

It demonstrates high generalization capability across different datasets.

The method effectively leverages statistical deviations for quality prediction.

Abstract

The statistical regularities of natural images, referred to as natural scene statistics, play an important role in no-reference image quality assessment. However, it has been widely acknowledged that screen content images (SCIs), which are typically computer generated, do not hold such statistics. Here we make the first attempt to learn the statistics of SCIs, based upon which the quality of SCIs can be effectively determined. The underlying mechanism of the proposed approach is based upon the mild assumption that the SCIs, which are not physically acquired, still obey certain statistics that could be understood in a learning fashion. We empirically show that the statistics deviation could be effectively leveraged in quality assessment, and the proposed method is superior when evaluated in different settings. Extensive experimental results demonstrate the Deep Feature Statistics based SCI Quality Assessment (DFSS-IQA) model delivers promising performance compared with existing NR-IQA models and shows a high generalization capability in the cross-dataset settings. The implementation of our method is publicly available at https://github.com/Baoliang93/DFSS-IQA.