US 12,223,541 B2
Virtual try-on system, virtual try-on method, computer program product, and information processing device
Hiroki Ueda, Suginami (JP); and Hisao Yoshioka, Chofu (JP)
Assigned to Kabushiki Kaisha Toshiba, Tokyo (JP); and Toshiba Digital Solutions Corporation, Kawasaki (JP)
Filed by KABUSHIKI KAISHA TOSHIBA, Minato-ku (JP); and TOSHIBA DIGITAL SOLUTIONS CORPORATION, Kawasaki (JP)
Filed on Aug. 18, 2020, as Appl. No. 16/995,873.
Application 16/995,873 is a continuation of application No. PCT/JP2018/041860, filed on Nov. 12, 2018.
Claims priority of application No. 2018-029041 (JP), filed on Feb. 21, 2018.
Prior Publication US 2020/0380594 A1, Dec. 3, 2020
Int. Cl. G06Q 30/0601 (2023.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01); G06V 10/56 (2022.01); G06V 10/60 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 40/10 (2022.01)
CPC G06Q 30/0643 (2013.01) [G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06V 10/56 (2022.01); G06V 10/60 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 40/103 (2022.01)] 19 Claims
OG exemplary drawing
 
14. A virtual try-on method implemented by a computer, the method comprising:
photographing, by a photographing unit, a try-on person image;
acquiring, by a first acquisition unit of the computer, the try-on person image photographed by the photographing unit;
acquiring, by a second acquisition unit of the computer configured to perform further photographing, three-dimensional data of a try-on person by the further photographing;
learning, by machine learning using the three-dimensional data of the try-on person acquired by the second acquisition unit, a learning model using the try-on person image acquired by the first acquisition unit as input data of a teacher try-on person image, and using a body shape parameter indicating a body shape of the try-on person represented by the teacher try-on person image and compositing position information indicating a compositing position of a clothing image in the teacher try-on person image as output data;
deriving the output data including the compositing position information and the body shape parameter corresponding to the try-on person represented by the try-on person image using the try-on person image and the learning model; and
generating a virtual try-on image by compositing the try-on person image and the clothing image using the derived output data, wherein
the photographing unit and the second acquisition unit are controlled to perform photographing in synchronization with each other to acquire the try-on person image by the first acquisition unit and acquire the three-dimensional data by the second acquisition unit.