Multitask Auxiliary Network for Perceptual Quality Assessment of Non-Uniformly Distorted Omnidirectional Images

TL;DR

This paper introduces a multitask auxiliary network designed to improve perceptual quality assessment of non-uniformly distorted omnidirectional images, addressing limitations of existing methods that focus mainly on uniform distortions.

Contribution

The proposed model effectively captures non-uniform distortions by jointly training main and auxiliary tasks, with a feature selection module enhancing performance over state-of-the-art metrics.

Findings

Outperforms existing OIQA metrics on large-scale databases

Auxiliary sub-networks significantly boost model accuracy

Dynamic feature allocation improves distortion detection

Abstract

Omnidirectional image quality assessment (OIQA) has been widely investigated in the past few years and achieved much success. However, most of existing studies are dedicated to solve the uniform distortion problem in OIQA, which has a natural gap with the non-uniform distortion problem, and their ability in capturing non-uniform distortion is far from satisfactory. To narrow this gap, in this paper, we propose a multitask auxiliary network for non-uniformly distorted omnidirectional images, where the parameters are optimized by jointly training the main task and other auxiliary tasks. The proposed network mainly consists of three parts: a backbone for extracting multiscale features from the viewport sequence, a multitask feature selection module for dynamically allocating specific features to different tasks, and auxiliary sub-networks for guiding the proposed model to capture local distortion and global quality change. Extensive experiments conducted on two large-scale OIQA databases demonstrate that the proposed model outperforms other state-of-the-art OIQA metrics, and these auxiliary sub-networks contribute to improve the performance of the proposed model. The source code is available at https://github.com/RJL2000/MTAOIQA.