Reference of neural network model for adaptation of 2d video for streaming to heterogeneous client end-points

A device for streaming immersive media, the device comprising:

• at least one memory configured to store program code;
• and
• at least one processor configured to read the program code and operate as instructed by the program code, the program code including:
• first receiving code configured to cause the at least one processor to receive, from a client end-point, a video content request that identifies video content;
• transmitting code configured to cause the at least one processor to transmit, to the client end-point based on the video content request, a profile request;
• second receiving code configured to cause the at least one processor to receive, from the client end-point, at least one neural network model associated with one or more characteristics of the client end-point;
• ingesting code configured to cause the at least one processor to ingest the identified video content in a two-dimensional video format;
• converting code configured to cause the at least one processor to convert the ingested video content to a three-dimensional video format based on the at least one neural network model such that the ingested video content converted to the three-dimensional video format includes at least one scene interpolated from one or more scenes of the ingested video content in the two-dimensional video format;
• and
• streaming code configured to cause the at least one processor to stream the converted video content to the client end-point.

A non-transitory computer-readable medium storing instructions, the instructions comprising:

• one or more instructions that, when executed by at least one processor of a device for streaming immersive media, cause the at least one processor to:
• receive, from a client end-point, a video content request that identifies video content;
• transmit, to the client end-point based on the video content request, a profile request;
• receive, from the client end-point, at least one neural network model associated with one or more characteristics of the client end-point;
• ingest identified video content in a two-dimensional video format;
• convert the ingested video content to a three-dimensional video format based on the at least one neural network model such that the ingested video content converted to the three-dimensional video format includes at least one scene interpolated from one or more scenes of the ingested video content in the two-dimensional video format;
• and
• stream the converted content to the client end-point.