VR IQA NET: Deep Virtual Reality Image Quality Assessment using Adversarial Learning

TL;DR

This paper introduces a deep learning-based VR image quality assessment method that uses adversarial learning to better predict perceived quality of omnidirectional images, outperforming existing metrics.

Contribution

It presents a novel VR IQA framework with a quality score predictor and human perception guider, tailored for omnidirectional images, utilizing adversarial learning for improved accuracy.

Findings

Outperforms existing 2D and VR IQA metrics

Effective in predicting human perceptual scores

Validated through extensive subjective experiments

Abstract

In this paper, we propose a novel virtual reality image quality assessment (VR IQA) with adversarial learning for omnidirectional images. To take into account the characteristics of the omnidirectional image, we devise deep networks including novel quality score predictor and human perception guider. The proposed quality score predictor automatically predicts the quality score of distorted image using the latent spatial and position feature. The proposed human perception guider criticizes the predicted quality score of the predictor with the human perceptual score using adversarial learning. For evaluation, we conducted extensive subjective experiments with omnidirectional image dataset. Experimental results show that the proposed VR IQA metric outperforms the 2-D IQA and the state-of-the-arts VR IQA.