Reference-Free Image Quality Metric for Degradation and Reconstruction Artifacts

TL;DR

This paper introduces a lightweight, reference-free neural network that predicts JPEG quality factors to assess image quality and artifacts, applicable across various image degradation and reconstruction tasks.

Contribution

A novel self-supervised neural network model that estimates image quality without references by predicting JPEG quality factors, generalizing to multiple artifact types.

Findings

Accurately predicts JPEG quality factors from image patches.

Generalizes to measure various artifacts like blur and noise.

Applies to MRI image reconstruction quality assessment.

Abstract

Image Quality Assessment (IQA) is essential in various Computer Vision tasks such as image deblurring and super-resolution. However, most IQA methods require reference images, which are not always available. While there are some reference-free IQA metrics, they have limitations in simulating human perception and discerning subtle image quality variations. We hypothesize that the JPEG quality factor is representatives of image quality measurement, and a well-trained neural network can learn to accurately evaluate image quality without requiring a clean reference, as it can recognize image degradation artifacts based on prior knowledge. Thus, we developed a reference-free quality evaluation network, dubbed "Quality Factor (QF) Predictor", which does not require any reference. Our QF Predictor is a lightweight, fully convolutional network comprising seven layers. The model is trained in a self-supervised manner: it receives JPEG compressed image patch with a random QF as input, is trained to accurately predict the corresponding QF. We demonstrate the versatility of the model by applying it to various tasks. First, our QF Predictor can generalize to measure the severity of various image artifacts, such as Gaussian Blur and Gaussian noise. Second, we show that the QF Predictor can be trained to predict the undersampling rate of images reconstructed from Magnetic Resonance Imaging (MRI) data.