CPC G06T 3/06 (2024.01) [G06F 18/213 (2023.01); G06N 3/02 (2013.01)] | 20 Claims |
1. A method comprising:
acquiring 3D content comprising a 3D object in 3D space, wherein the 3D object has object information indicative of a location of the 3D object in the 3D space;
rendering a 2D image comprising a 2D object in 2D space by projecting the 3D object from the 3D space to the 2D space based on the object information, wherein the 2D object has one or more 2D vertices indicative of a location of the 2D object in the 2D space;
determining one or more latent variables in the 2D space based on the object information and the one or more 2D vertices;
determining validity for the one or more 2D vertices based on a corresponding motion vector; and
generating a 2D feature database including the rendered 2D image and the one or more latent variables.
|