Image Quality Assessment: Learning to Rank Image Distortion Level

TL;DR

This paper introduces a deep learning approach to compare image quality by learning to rank images based on distortion levels, addressing the challenge of assessing perceptual quality without relying on explicit human visual system models.

Contribution

It proposes a neural network-based method to learn relative image quality rankings, improving assessment of distortions where HVS modeling is difficult.

Findings

Effective ranking of images with chromatic aberration and Moire distortions

Validated on synthetic and real datasets

Outperforms traditional quality assessment methods

Abstract

Over the years, various algorithms were developed, attempting to imitate the Human Visual System (HVS), and evaluate the perceptual image quality. However, for certain image distortions, the functionality of the HVS continues to be an enigma, and echoing its behavior remains a challenge (especially for ill-defined distortions). In this paper, we learn to compare the image quality of two registered images, with respect to a chosen distortion. Our method takes advantage of the fact that at times, simulating image distortion and later evaluating its relative image quality, is easier than assessing its absolute value. Thus, given a pair of images, we look for an optimal dimensional reduction function that will map each image to a numerical score, so that the scores will reflect the image quality relation (i.e., a less distorted image will receive a lower score). We look for an optimal dimensional reduction mapping in the form of a Deep Neural Network which minimizes the violation of image quality order. Subsequently, we extend the method to order a set of images by utilizing the predicted level of the chosen distortion. We demonstrate the validity of our method on Latent Chromatic Aberration and Moire distortions, on synthetic and real datasets.