公开(公告)号：US11727710B2

公开(公告)日：2023-08-15

申请号：US17508384

申请日：2021-10-22

Applicant: Snap Inc.

Inventor： Yuncheng Li ,  Linjie Yang ,  Ning Zhang ,  Zhengyuan Yang

IPC: G06V40/10 ,  G06F17/15 ,  G06T7/136 ,  G06N3/04

CPC classification number: G06V40/107 ,  G06F17/15 ,  G06N3/04 ,  G06T7/136

Abstract: Segmentation of an image into individual body parts is performed based on a trained model. The model is trained with a plurality of training images, each training image representing a corresponding training figure. The model is also trained with a corresponding plurality of segmentations of the training figures. Each segmentation is generated by positioning body parts between defined positions of joints of the represented figure. The body parts are represented by body part templates obtained from a template library, with the templates defining characteristics of body parts represented by the templates.

公开(公告)号：US20230290174A1

公开(公告)日：2023-09-14

申请号：US18318556

申请日：2023-05-16

Applicant: Snap Inc.

Inventor： Yuncheng Li ,  Linjie Yang ,  Ning Zhang ,  Zhengyuan Yang

IPC: G06V40/10 ,  G06F17/15 ,  G06N3/04 ,  G06T7/136

CPC classification number: G06V40/107 ,  G06F17/15 ,  G06N3/04 ,  G06T7/136

Abstract: Segmentation of an image into individual body parts is performed based on a trained model. The model is trained with a plurality of training images, each training image representing a corresponding training figure. The model is also trained with a corresponding plurality of segmentations of the training figures. Each segmentation is generated by positioning body parts between defined positions of joints of the represented figure. The body parts are represented by body part templates obtained from a template library, with the templates defining characteristics of body parts represented by the templates.

公开(公告)号：US11182603B1

公开(公告)日：2021-11-23

申请号：US16450376

申请日：2019-06-24

Applicant: Snap Inc.

Inventor： Yuncheng Li ,  Linjie Yang ,  Ning Zhang ,  Zhengyuan Yang

IPC: G06K9/00 ,  G06F17/15 ,  G06N3/04 ,  G06T7/136

Abstract: Segmentation of an image into individual body parts is performed based on a trained model. The model is trained with a plurality of training images, each training image representing a corresponding training figure. The model is also trained with a corresponding plurality of segmentations of the training figures. Each segmentation is generated by positioning body parts between defined positions of joints of the represented figure. The body parts are represented by body part templates obtained from a template library, with the templates defining characteristics of body parts represented by the templates.