Visual Attention in Omnidirectional Video for Virtual Reality Applications

Understanding of visual attention is crucial for omnidirectional video (ODV) viewed for instance with a head-mounted display (HMD), where only a fraction of an ODV is rendered at a time. Transmission and rendering of ODV can be optimized by understanding how viewers consume a given ODV in virtual reality (VR) applications. In order to predict video regions that might draw the attention of viewers, saliency maps can be estimated by using computational visual attention models. As no such model currently exists for ODV, but given the importance for emerging ODV applications, we create a new visual attention user dataset for ODV, investigate behavior of viewers when consuming the content, and analyze the prediction performance of state-of-the-art visual attention models. Our developed test-bed and dataset will be publicly available with this paper, to stimulate and support research on ODV.