US 12,450,853 B2
Method and system for generating virtual content
Hyukjae Jang, Seongnam-si (KR); and Hoyoung Cho, Seongnam-si (KR)
Assigned to LINE Plus Corporation, Seongnam-si (KR)
Filed by LINE Plus Corporation, Seongnam-si (KR)
Filed on Jul. 21, 2023, as Appl. No. 18/356,318.
Claims priority of application No. 10-2022-0103488 (KR), filed on Aug. 18, 2022.
Prior Publication US 2024/0062497 A1, Feb. 22, 2024
Int. Cl. G06T 19/20 (2011.01); G06T 7/194 (2017.01); G06T 7/20 (2017.01); G06T 7/70 (2017.01)
CPC G06T 19/20 (2013.01) [G06T 7/194 (2017.01); G06T 7/20 (2013.01); G06T 7/70 (2017.01); G06T 2219/2004 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method of generating virtual content by one or more processors, the method comprising:
receiving video content;
extracting, by the one or more processors, first motion data of a first object included in the video content; and
converting, by the one or more processors, the video content in accordance with a first virtual environment based on the first motion data of the first object to generate the virtual content in the first virtual environment,
wherein the generating the virtual content in the first virtual environment comprises:
generating second motion data in the first virtual environment based on the first motion data,
wherein the generating the second motion data in the first virtual environment comprises:
inputting the first motion data to a first machine learning model,
wherein the first machine learning model is a machine learning model trained with first training data and second training data to generate the second motion data in the first virtual environment,
the first training data includes motion data extracted from the video content for training, and
the second training data includes motion data for training in the first virtual environment.