CPC G06T 17/00 (2013.01) [G06F 30/10 (2020.01); G06T 7/10 (2017.01); G06T 7/62 (2017.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06T 15/04 (2013.01); G06T 17/10 (2013.01); G06T 17/20 (2013.01); G06T 17/30 (2013.01); G06V 10/761 (2022.01); G06V 20/64 (2022.01); G06F 30/12 (2020.01); G06N 20/20 (2019.01); G06T 2207/20044 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30196 (2013.01)] | 20 Claims |
1. A method comprising:
receiving a material image, the material image comprising a two-dimensional (2D) color image depicting a physical material;
identifying a material class of the physical material based on the material image, the material class indicative of a type of material for the physical material;
identifying a texture map model corresponding to the material class, the texture map model comprising a machine-learning model trained to generate texture maps based on material images of physical materials of the corresponding material class; and
generating a set of texture maps based on the material image through application of the texture map model to the material image, each texture map in the set of texture maps comprising a set of texture values for the physical material.
|