UNIQUE: Unsupervised Image Quality Estimation

TL;DR

UNIQUE is an unsupervised image quality estimator leveraging sparse representations from generic image databases, achieving top performance across multiple benchmark datasets in accuracy and consistency.

Contribution

This paper introduces UNIQUE, a novel unsupervised image quality estimation method based on sparse representations learned from large-scale image data.

Findings

UNIQUE outperforms thirteen existing quality estimators on benchmark datasets.

The method demonstrates high accuracy, consistency, and linearity in quality assessment.

Sparse representations effectively capture perceptual image quality features.

Abstract

In this paper, we estimate perceived image quality using sparse representations obtained from generic image databases through an unsupervised learning approach. A color space transformation, a mean subtraction, and a whitening operation are used to enhance descriptiveness of images by reducing spatial redundancy; a linear decoder is used to obtain sparse representations; and a thresholding stage is used to formulate suppression mechanisms in a visual system. A linear decoder is trained with 7 GB worth of data, which corresponds to 100,000 8x8 image patches randomly obtained from nearly 1,000 images in the ImageNet 2013 database. A patch-wise training approach is preferred to maintain local information. The proposed quality estimator UNIQUE is tested on the LIVE, the Multiply Distorted LIVE, and the TID 2013 databases and compared with thirteen quality estimators. Experimental results show that UNIQUE is generally a top performing quality estimator in terms of accuracy, consistency, linearity, and monotonic behavior.