Omnidirectional Image Quality Assessment by Distortion Discrimination Assisted Multi-Stream Network

Omnidirectional image (OI) quality assessment is crucial to facilitate the development of virtual reality (VR) related technology. In this work, a distortion discrimination assisted multi-stream network is proposed for OI quality assessment. The multi-stream architecture is constructed by generating the viewport images received by the retina at one point to simulate the characteristics of humans perceiving VR contents. Additionally, the strategy of generating several viewport image sets from one OI is proposed for data augmentation. Furthermore, the facts that the human brain has the ability for both quality assessment and distortion type distinguishment, and the process of human brain handling two tasks exists information interaction inspire us to employ an auxiliary distortion discrimination task to facilitate the quality assessment task learning. Extensive experiments conducted on two public OI databases demonstrate the superiority of the proposed method to both traditional 2D quality metrics and existing metrics specific for OIs. Moreover, utilizing the assistant task is proven to be more effective than the single task learning for OI quality evaluation. Better generalization performance is also verified to be another valuable trait of the proposed method.

Automated summary

In this study, a distortion discrimination assisted multi-stream network is proposed for omnidirectional image (OI) quality assessment. The multi-stream architecture simulates human perception of VR contents using generated viewport images. Data augmentation strategy is employed to generate multiple viewport image sets from one OI. By utilizing an auxiliary distortion discrimination task, the proposed method improves the learning of the quality assessment task. Extensive experiments demonstrate the superiority of this method to traditional 2D quality metrics and existing metrics specific for OIs. Additionally, utilizing the assistant task is proven to be more effective for OI quality evaluation and the proposed method exhibits better generalization performance.