Spatial Attention-based Non-reference Perceptual Quality Prediction Network for Omnidirectional Images
This work addresses the challenge of non-reference quality assessment for omnidirectional images, which is important for applications like virtual reality, by providing a more accessible and efficient method, though it is incremental as it builds on existing attention mechanisms.
The paper tackles the problem of predicting perceptual quality for omnidirectional images without requiring human saliency labels, which are hard to obtain, by proposing a spatial attention-based network (SAP-net) and establishing a large-scale dataset (IQA-ODI) with 1,080 images and 200 subjects; the network outperforms 9 state-of-the-art methods and reduces computational complexity.
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}.