Spatial Attention-based Non-reference Perceptual Quality Prediction Network for Omnidirectional Images

TL;DR

This paper introduces SAP-net, a spatial attention-based deep learning model that predicts perceptual quality of omnidirectional images without human saliency labels, using a large-scale dataset for training and outperforming existing methods.

Contribution

The paper presents a novel self-attention based network for non-reference quality assessment of ODIs, eliminating the need for human saliency labels and reducing computational complexity.

Findings

SAP-net outperforms 9 state-of-the-art methods.

The large-scale IQA-ODI dataset enables effective training.

The method achieves high accuracy without human saliency labels.

Abstract

Due to the strong correlation between visual attention and perceptual quality, many methods attempt to use human saliency information for image quality assessment. Although this mechanism can get good performance, the networks require human saliency labels, which is not easily accessible for omnidirectional images (ODI). To alleviate this issue, we propose a spatial attention-based perceptual quality prediction network for non-reference quality assessment on ODIs (SAP-net). To drive our SAP-net, we establish a large-scale IQA dataset of ODIs (IQA-ODI), which is composed of subjective scores of 200 subjects on 1,080 ODIs. In IQA-ODI, there are 120 high quality ODIs as reference, and 960 ODIs with impairments in both JPEG compression and map projection. Without any human saliency labels, our network can adaptively estimate human perceptual quality on impaired ODIs through a self-attention manner, which significantly promotes the prediction performance of quality scores. Moreover, our method greatly reduces the computational complexity in quality assessment task on ODIs. Extensive experiments validate that our network outperforms 9 state-of-the-art methods for quality assessment on ODIs. The dataset and code have been available on \url{ https://github.com/yanglixiaoshen/SAP-Net}.