US 12,262,070 B2
Reference of neural network model for adaptation of 2D video for streaming to heterogeneous client end-points
Arianne Hinds, Palo Alto, CA (US); and Stephan Wenger, Hillsborough, CA (US)
Assigned to TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed by TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed on Jun. 2, 2023, as Appl. No. 18/205,013.
Application 18/205,013 is a continuation of application No. 17/407,711, filed on Aug. 20, 2021, granted, now 11,736,748.
Claims priority of provisional application 63/126,188, filed on Dec. 16, 2020.
Prior Publication US 2023/0319328 A1, Oct. 5, 2023
Int. Cl. H04N 21/235 (2011.01); H04N 21/81 (2011.01)
CPC H04N 21/2356 (2013.01) [H04N 21/816 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of streaming immersive media, executable by a processor, the method comprising:
ingesting content in a two-dimensional format, wherein the two-dimensional format references at least one neural network, wherein the ingested content includes a scene that includes a plurality of layers, wherein each layer of media objects that are referenced within a scene is associated with a token that points to an address where a resource is accessed within a network that ingests the content, wherein the plurality of layers comprises a base layer and an enhancement layer, wherein the enhancement layer modifies a property of a media object in the base layer such that the enhancement layer alters a surface or texture of the media object in the base layer from a first property to a second property;
converting the ingested content to a three-dimensional format based on the referenced at least one neural network; and
streaming the converted content to the client end-point.