Method and system for generating fusion reality scene based on virtual objects and real world objects represented from different vantage points in different video data streams

摘要

An exemplary fusion reality scene capture system ("system") receives a first frame set of surface data frames from a plurality of three dimensional ("3D") capture devices, the 3D capture device has multiple different vanes in the real world scene Disposed over the real world scene to have a table point.Based on the first frame set, the system generates a transport stream, wherein the transport stream comprises a color video data stream for each of the 3D capture devices, and a depth video data stream Including M.Based on the transport stream, the system generates entity description data and the entity description data represents multiple entities contained within the 3D space of the fusion reality scene.The plurality of entities include a virtual object, a real world object, and a virtual viewpoint to said 3D space, the second frame set of the surface data frame from said 3D space, said virtual object and said reality Rendered to represent color data and depth data for both the world object and the object.