CPC G06T 7/70 (2017.01) [G06N 3/08 (2013.01); G06V 20/56 (2022.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30252 (2013.01)] | 20 Claims |
1. A method comprising:
extracting, by a device, a first image from a second image based on a location of an object within the first image;
grouping, by the device, a series of probabilities associated with the first image into a first quantity of groups;
determining, by the device, a coarse-grained viewpoint estimate associated with the object based on grouping the series of probabilities into the first quantity of groups;
determining, by the device, a fine-grained viewpoint estimate associated with the object based on grouping the series of probabilities into a second quantity of groups,
wherein the second quantity of groups is greater than the first quantity of groups;
determining, by the device, an object viewpoint associated with the object based on at least one of the coarse-grained viewpoint estimate or the fine-grained viewpoint estimate; and
performing, by the device, one or more actions based on the object viewpoint.
|