Max360IQ: Blind Omnidirectional Image Quality Assessment with Multi-axis Attention

TL;DR

Max360IQ is a novel blind omnidirectional image quality assessment model that effectively measures both uniform and non-uniform distortions using multi-axis attention and multi-scale feature fusion, outperforming existing methods.

Contribution

The paper introduces Max360IQ, a new BOIQA model with multi-axis attention and multi-scale features, improving accuracy in assessing omnidirectional image quality under various distortions.

Findings

Outperforms state-of-the-art Assessor360 by 3.6% SRCC on JUFE database.

Achieves 0.4% and 0.8% SRCC improvements on OIQA and CVIQ databases.

Effective in assessing both uniform and non-uniform distortions in omnidirectional images.

Abstract

Omnidirectional image, also called 360-degree image, is able to capture the entire 360-degree scene, thereby providing more realistic immersive feelings for users than general 2D image and stereoscopic image. Meanwhile, this feature brings great challenges to measuring the perceptual quality of omnidirectional images, which is closely related to users' quality of experience, especially when the omnidirectional images suffer from non-uniform distortion. In this paper, we propose a novel and effective blind omnidirectional image quality assessment (BOIQA) model with multi-axis attention (Max360IQ), which can proficiently measure not only the quality of uniformly distorted omnidirectional images but also the quality of non-uniformly distorted omnidirectional images. Specifically, the proposed Max360IQ is mainly composed of a backbone with stacked multi-axis attention modules for capturing both global and local spatial interactions of extracted viewports, a multi-scale feature integration (MSFI) module to fuse multi-scale features and a quality regression module with deep semantic guidance for predicting the quality of omnidirectional images. Experimental results demonstrate that the proposed Max360IQ outperforms the state-of-the-art Assessor360 by 3.6\% in terms of SRCC on the JUFE database with non-uniform distortion, and gains improvement of 0.4\% and 0.8\% in terms of SRCC on the OIQA and CVIQ databases, respectively. The source code is available at https://github.com/WenJuing/Max360IQ.