Assessing Image Quality Using a Simple Generative Representation

TL;DR

This paper introduces VAE-QA, a simple auto-encoder based method for full-reference image quality assessment that outperforms existing techniques in generalization, efficiency, and speed.

Contribution

It proposes a novel approach leveraging auto-encoders for perceptual IQA, improving cross-dataset generalization and computational efficiency.

Findings

Significantly better generalization across datasets.

Fewer trainable parameters and smaller memory footprint.

Faster runtime compared to state-of-the-art methods.

Abstract

Perceptual image quality assessment (IQA) is the task of predicting the visual quality of an image as perceived by a human observer. Current state-of-the-art techniques are based on deep representations trained in discriminative manner. Such representations may ignore visually important features, if they are not predictive of class labels. Recent generative models successfully learn low-dimensional representations using auto-encoding and have been argued to preserve better visual features. Here we leverage existing auto-encoders and propose VAE-QA, a simple and efficient method for predicting image quality in the presence of a full-reference. We evaluate our approach on four standard benchmarks and find that it significantly improves generalization across datasets, has fewer trainable parameters, a smaller memory footprint and faster run time.