Video data processing method and apparatus, computer device, computer readable storage medium, and computer program product

An apparatus for data processing, the apparatus comprising:

• processing circuitry configured to
• generate, based on a spliced texture map and a depth map, an encoded video bitstream for constructing a free-view video, the spliced texture map and the depth map being based on multiple images collected by an ith camera in a camera array, the camera array comprising N cameras, and i being a positive integer less than or equal to N;
• obtain boundary metadata information indicating a scene boundary of the free-view video, the boundary metadata information being indicated by a boundary information data box that corresponds to the scene boundary, the boundary information data box being determined based on at least one of camera parameter information, cross-boundary processing information, and boundary range information of a jth boundary camera of M boundary cameras in the camera array, the boundary range information indicating a rendering region range for rendering the scene boundary;
• add the boundary metadata information to a file encapsulation data box corresponding to the free-view video, to obtain an extended data box;
• perform encapsulation processing on the encoded video bitstream and the extended data box to obtain a video media file of the free-view video including the boundary metadata information;
• and
• deliver the video media file to a video client that is configured to determine that the ith camera is a boundary camera, and to render video content in the scene boundary indicated by the boundary metadata information.

A non-transitory computer-readable storage medium storing computer-readable instructions thereon, which, when executed by processing circuitry, cause the processing circuitry to perform a video data processing method comprising:

• generating, based on a spliced texture map and a depth map, an encoded video bitstream for constructing a free-view video, the spliced texture map and the depth map being based on multiple images collected by an ith camera in a camera array, the camera array comprising N cameras, and i being a positive integer less than or equal to N;
• obtaining boundary metadata information indicating a scene boundary of the free-view video, the boundary metadata information being indicated by a boundary information data box that corresponds to the scene boundary, the boundary information data box being determined based on at least one of camera parameter information, cross-boundary processing information, and boundary range information of a jth boundary camera of M boundary cameras in the camera array, the boundary range information indicating a rendering region range for rendering the scene boundary;
• adding the boundary metadata information to a file encapsulation data box corresponding to the free-view video, to obtain an extended data box;
• performing encapsulation processing on the encoded video bitstream and the extended data box to obtain a video media file of the free-view video including the boundary metadata information;
• and
• delivering the video media file to a video client that is configured to determine that the ith camera is a boundary camera, and to render video content in the scene boundary indicated by the boundary metadata information.