JSTSP Volume 14 Issue 1

Panoramic videos are becoming more and more easily obtained for common users. Although these videos have 360∘ field of view, they are usually displayed with perspective views, which needs the saliency informations for viewing angle selection. In this paper, we propose a saliency prediction network for 360∘ videos. Our network takes video frames and optical flows in cube map format as input, thus it does not suffer from image distorations of panoramic frames. 

Panoramic videos are becoming more and more easily obtained for common users. Although these videos have 360∘ field of view, they are usually displayed with perspective views, which needs the saliency informations for viewing angle selection. In this paper, we propose a saliency prediction network for 360∘ videos. Our network takes video frames and optical flows in cube map format as input, thus it does not suffer from image distorations of panoramic frames. 

Nowadays, 360° video/image has been increasingly popular and drawn great attention. The spherical viewing range of 360° video/image accounts for huge data, which pose the challenges to 360° video/image processing in solving the bottleneck of storage, transmission, etc. Accordingly, the recent years have witnessed the explosive emergence of works on 360° video/image processing.

Recent years have witnessed the rapid development of virtual reality (VR). Above 90% of VR content is in the form of 360° video, also called omnidirectional video or panoramic video. Generally speaking, 360° video offers immersive and interactive viewing experience, as the viewers are able to freely move their heads in the range of 360° × 180° to access different viewports.