US 12,307,589 B2
Generating semantically-labelled three-dimensional models
Yan Deng, La Jolla, CA (US); Ze Zhang, San Diego, CA (US); Michel Adib Sarkis, San Diego, CA (US); and Ning Bi, San Diego, CA (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Mar. 21, 2023, as Appl. No. 18/187,595.
Prior Publication US 2024/0320909 A1, Sep. 26, 2024
Int. Cl. G06T 17/00 (2006.01); G06T 7/10 (2017.01); G06T 19/00 (2011.01)
CPC G06T 17/00 (2013.01) [G06T 7/10 (2017.01); G06T 19/003 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2219/004 (2013.01)] 30 Claims
OG exemplary drawing
 
1. An apparatus for generating one or more three-dimensional models, the apparatus comprising:
at least one memory; and
at least one processor coupled to the at least one memory and configured to:
obtain a plurality of images of an object;
obtain a plurality of segmentation masks associated with the plurality of images, each segmentation mask of the plurality of segmentation masks including at least one label indicative of at least one segment of the object in a respective image of the plurality of images;
train, using the plurality of images and the plurality of segmentation masks, a machine-learning model to generate one or more semantically-labeled three-dimensional models of the object; and
generate using the trained machine-learning model, a semantically-labeled three-dimensional model of the object, the semantically-labeled three-dimensional model of the object including at least one label indicative of the at least one segment of the object.