US 11,747,892 B2
Systems and methods for predicting lower body poses
Benjamin Antoine Georges Lefaudeux, Menlo Park, CA (US); Samuel Alan Johnson, San Carlos, CA (US); Carsten Sebastian Stoll, San Francisco, CA (US); and Kishore Venkateshan, Foster City, CA (US)
Assigned to Meta Platforms Technologies, LLC, Menlo Park, CA (US)
Filed by Meta Platforms Technologies, LLC, Menlo Park, CA (US)
Filed on Nov. 21, 2022, as Appl. No. 18/57,561.
Application 18/057,561 is a continuation of application No. 17/024,591, filed on Sep. 17, 2020, granted, now 11,507,179.
Prior Publication US 2023/0077772 A1, Mar. 16, 2023
Int. Cl. G06F 3/01 (2006.01); G06T 7/70 (2017.01); G06N 20/00 (2019.01); G06N 5/04 (2023.01); G06F 3/0346 (2013.01)
CPC G06F 3/011 (2013.01) [G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06T 7/70 (2017.01); G06F 3/0346 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30196 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising, by a computing system:
receiving sensor data captured at a first time by one or more sensors coupled to a user;
generating, based on the sensor data, a first upper body pose associated with the first time, wherein the first upper body pose corresponds to a first portion of a body of the user, the first portion of the body comprising a head and an arm of the user;
generating a temporal sequence of lower body poses comprising a first lower body pose associated with the first time and a second lower body pose associated with a second time by processing the first upper body pose using a machine-learning model, wherein the temporal sequence of lower body poses correspond to a second portion of the body of the user, the second portion of the body comprising a leg of the user;
generating one or more full body poses of the user based on at least the first upper body pose and the temporal sequence of lower body poses.