Assessing Image Quality Using a Simple Generative Representation
This addresses image quality evaluation for applications like media processing, though it is incremental as it builds on existing auto-encoders.
The paper tackled perceptual image quality assessment by proposing VAE-QA, a method using auto-encoders to predict image quality with a full-reference, which improved generalization across datasets, reduced parameters, memory, and run time.
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.