US 11,748,913 B2
Modeling objects from monocular camera outputs
Ashar Ali, San Diego, CA (US); Gokce Dane, San Diego, CA (US); Upal Mahbub, San Diego, CA (US); Samuel Sunarjo, San Diego, CA (US); and Gerhard Reitmayr, Del Mar, CA (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Mar. 1, 2021, as Appl. No. 17/189,105.
Prior Publication US 2022/0277489 A1, Sep. 1, 2022
Int. Cl. G06N 3/08 (2023.01); G06T 17/00 (2006.01); G06T 17/20 (2006.01); G06T 7/00 (2017.01); G06T 7/80 (2017.01)
CPC G06T 7/97 (2017.01) [G06N 3/08 (2013.01); G06T 7/80 (2017.01); G06T 17/20 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 28 Claims
OG exemplary drawing
 
1. A apparatus comprising:
memory; and
one or more processors coupled to the memory, the one or more processors being configured to:
update one or more parameters associated with a neural network system based on one or more losses associated with a 3D mesh of a target;
receive metadata and an image of the target in a real-world scene, the metadata associated with at least one of the image and an image capture device that captured the image;
determine, based on the image and the metadata, first three-dimensional (3D) mesh parameters of a first 3D mesh of the target the first 3D mesh parameters and the first 3D mesh corresponding to a first reference frame associated with at least one of the image and the image capture device; and
determine, based on the first 3D mesh parameters and the updated one or more parameters associated with the neural network system, second 3D mesh parameters for a second 3D mesh of the target, the second 3D mesh parameters and the second 3D mesh corresponding to a second reference frame, the second reference frame corresponding to a 3D coordinate system of the real-world scene.