A Probabilistic Quality Representation Approach to Deep Blind Image Quality Prediction

TL;DR

This paper introduces a probabilistic quality representation for deep blind image quality assessment, improving training robustness and prediction accuracy by modeling subjective score distributions instead of scalar scores.

Contribution

It proposes a novel probabilistic quality representation (PQR) that captures subjective score distributions, enhancing deep BIQA model training and performance.

Findings

PQR speeds up model training convergence.

PQR significantly improves quality prediction accuracy.

The method outperforms scalar score regression approaches.

Abstract

Blind image quality assessment (BIQA) remains a very challenging problem due to the unavailability of a reference image. Deep learning based BIQA methods have been attracting increasing attention in recent years, yet it remains a difficult task to train a robust deep BIQA model because of the very limited number of training samples with human subjective scores. Most existing methods learn a regression network to minimize the prediction error of a scalar image quality score. However, such a scheme ignores the fact that an image will receive divergent subjective scores from different subjects, which cannot be adequately represented by a single scalar number. This is particularly true on complex, real-world distorted images. Moreover, images may broadly differ in their distributions of assigned subjective scores. Recognizing this, we propose a new representation of perceptual image quality, called probabilistic quality representation (PQR), to describe the image subjective score distribution, whereby a more robust loss function can be employed to train a deep BIQA model. The proposed PQR method is shown to not only speed up the convergence of deep model training, but to also greatly improve the achievable level of quality prediction accuracy relative to scalar quality score regression methods. The source code is available at https://github.com/HuiZeng/BIQA_Toolbox.