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, at a model generation system, an object image depicting an object;
identifying a set of parts of the object based on the object image;
for each part in the set of parts:
identifying a part type for the part, the part type being one of a set of part types associated with the object;
accessing a plurality of candidate part models associated with the identified part type, wherein each part model of the plurality of candidate part models is a three-dimensional model of an object part of the identified part type;
generating a similarity score for each part model of a plurality of candidate part models stored by the model generation system, wherein the similarity score for a part model is generated by:
accessing a plurality of model images associated with the part model; and
comparing the object image to each of the plurality of model images; and
selecting a part model for the part based on the similarity score of each part model of the plurality of candidate part models; and
generating a three-dimensional (3D) object model for the object based on an identified part model for each part in the set of parts.
|