US 12,413,633 B2
Reference of neural network model by immersive media for adaptation of media for streaming to heterogenous client end-points
Arianne Hinds, Palo Alto, CA (US); and Stephan Wenger, Palo Alto, CA (US)
Assigned to TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed by TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed on Feb. 5, 2024, as Appl. No. 18/432,858.
Application 18/432,858 is a continuation of application No. 17/407,816, filed on Aug. 20, 2021, granted, now 11,943,271.
Claims priority of provisional application 63/127,036, filed on Dec. 17, 2020.
Prior Publication US 2024/0179203 A1, May 30, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 65/612 (2022.01); G06N 3/02 (2006.01); G06T 7/55 (2017.01); H04L 65/75 (2022.01)
CPC H04L 65/612 (2022.05) [G06N 3/02 (2013.01); G06T 7/55 (2017.01); H04L 65/75 (2022.05); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method of streaming immersive media, executable by a processor, comprising:
ingesting content in a first two-dimensional format or a first three-dimension format, the content comprising one or more SEI messages,
wherein the one or more SEI message comprises a reference to a neural network model for converting the content, the reference comprising an identifier to the neural network model for converting the content and one or more parameters of the neural network model, wherein the reference indicates that the neural network model is associated with a scene in the content; and wherein when the reference comprises an identifier to the neural network model for converting the content and one or more parameters of the neural network model, the reference indicates that the neural network model for converting the content and the one or more parameters of the neural network model are stored outside of the content; and
converting the content to a second two-dimensional or a second three-dimensional format based on the referenced neural network model.