公开(公告)号：US20210074016A1

公开(公告)日：2021-03-11

申请号：US17015819

申请日：2020-09-09

Applicant: Snap Inc.

Inventor： Yuncheng Li ,  Jonathan M. Rodriguez, II ,  Zehao Xue ,  Yingying Wang

IPC: G06T7/73 ,  G06T7/20 ,  G06F3/01 ,  H04N13/204 ,  G06K9/00 ,  G06K9/62

Abstract: Systems and methods herein describe using a neural network to identify a first set of joint location coordinates and a second set of joint location coordinates and identifying a three-dimensional hand pose based on both the first and second sets of joint location coordinates.

公开(公告)号：US20200184721A1

公开(公告)日：2020-06-11

申请号：US16210927

申请日：2018-12-05

Applicant: Snap Inc.

Inventor： Liuhao Ge ,  Zhou Ren ,  Yuncheng Li ,  Zehao Xue ,  Yingying Wang

IPC: G06T17/20 ,  G06T7/73 ,  G06N3/04 ,  G06N3/08

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for receiving a monocular image that includes a depiction of a hand and extracting features of the monocular image using a plurality of machine learning techniques. The program and method further include modeling, based on the extracted features, a pose of the hand depicted in the monocular image by adjusting skeletal joint positions of a three-dimensional (3D) hand mesh using a trained graph convolutional neural network (CNN); modeling, based on the extracted features, a shape of the hand in the monocular image by adjusting blend shape values of the 3D hand mesh representing surface features of the hand depicted in the monocular image using the trained graph CNN; and generating, for display, the 3D hand mesh adjusted to model the pose and shape of the hand depicted in the monocular image.