Bridging the Gap Between Saliency Prediction and Image Quality Assessment

TL;DR

This paper explores the connection between saliency prediction and image quality assessment, revealing that IQA models incorporate saliency knowledge, and introduces a new dataset for saliency-aware image quality evaluation.

Contribution

It empirically demonstrates the relationship between saliency prediction and IQA, and introduces the SACID dataset for saliency-aware image quality assessment.

Findings

IQA models incorporate saliency information.

A new dataset for saliency-aware IQA is introduced.

Comparison of classic and neural IQA methods conducted.

Abstract

Over the past few years, deep neural models have made considerable advances in image quality assessment (IQA). However, the underlying reasons for their success remain unclear, owing to the complex nature of deep neural networks. IQA aims to describe how the human visual system (HVS) works and to create its efficient approximations. On the other hand, Saliency Prediction task aims to emulate HVS via determining areas of visual interest. Thus, we believe that saliency plays a crucial role in human perception. In this work, we conduct an empirical study that reveals the relation between IQA and Saliency Prediction tasks, demonstrating that the former incorporates knowledge of the latter. Moreover, we introduce a novel SACID dataset of saliency-aware compressed images and conduct a large-scale comparison of classic and neural-based IQA methods. All supplementary code and data will be available at the time of publication.