US 12,293,444 B2
Music reactive animation of human characters
Gurunandan Krishnan Gorumkonda, Kirkland, WA (US); Hsin-Ying Lee, San Jose, CA (US); and Jie Xu, Cambridge, MA (US)
Assigned to Snap Inc., Santa Monica, CA (US)
Filed by Snap Inc., Santa Monica, CA (US)
Filed on Oct. 6, 2023, as Appl. No. 18/482,634.
Application 18/482,634 is a continuation of application No. 17/487,558, filed on Sep. 28, 2021, granted, now 11,816,773.
Claims priority of provisional application 63/085,755, filed on Sep. 30, 2020.
Prior Publication US 2024/0054709 A1, Feb. 15, 2024
Int. Cl. G06T 13/20 (2011.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06T 13/40 (2011.01); G06T 13/80 (2011.01)
CPC G06T 13/205 (2013.01) [G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06T 13/40 (2013.01); G06T 13/80 (2013.01); G10H 2210/031 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating an animated character in dance poses to music, the method comprising:
receiving, by at least one processor, a latent space comprising a distribution of possible poses for the animated character from an encoding neural network;
generating, by the at least one processor, current generated pose data using a decoding neural network, the current generated pose data being based on previous generated pose data of a previous generated pose, a music input signal, and the latent space; and
generating, by the at least one processor, the animated character based on the current generated pose data.