公开(公告)号：US11335023B2

公开(公告)日：2022-05-17

申请号：US15929811

申请日：2020-05-22

Applicant: Google LLC

Inventor： Sameh Khamis ,  Christian Haene ,  Hossam Isack ,  Cem Keskin ,  Sofien Bouaziz ,  Shahram Izadi

IPC: G06K9/00 ,  G06T7/73 ,  G06T3/40 ,  G06T11/00 ,  G06N3/08 ,  G06N3/04

Abstract: According to an aspect, a method for pose estimation using a convolutional neural network includes extracting features from an image, downsampling the features to a lower resolution, arranging the features into sets of features, where each set of features corresponds to a separate keypoint of a pose of a subject, updating, by at least one convolutional block, each set of features based on features of one or more neighboring keypoints using a kinematic structure, and predicting the pose of the subject using the updated sets of features.

公开(公告)号：US20210366146A1

公开(公告)日：2021-11-25

申请号：US15929811

申请日：2020-05-22

Applicant: Google LLC

Inventor： Sameh Khamis ,  Christian Haene ,  Hossam Isack ,  Cem Keskin ,  Sofien Bouaziz ,  Shahram Izadi

IPC: G06T7/73 ,  G06T3/40 ,  G06T11/00 ,  G06N3/04 ,  G06N3/08

Abstract: According to an aspect, a method for pose estimation using a convolutional neural network includes extracting features from an image, downsampling the features to a lower resolution, arranging the features into sets of features, where each set of features corresponds to a separate keypoint of a pose of a subject, updating, by at least one convolutional block, each set of features based on features of one or more neighboring keypoints using a kinematic structure, and predicting the pose of the subject using the updated sets of features.

公开(公告)号：US20210365777A1

公开(公告)日：2021-11-25

申请号：US16976805

申请日：2019-07-23

Applicant: Google LLC

Inventor： Shahram Izadi ,  Cem Keskin

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: Methods, systems, and apparatus for more efficiently and accurately generating neural network outputs, for instance, for use in classifying image or audio data. In one aspect, a method includes processing a network input using a neural network including multiple neural network layers to generate a network output. One or more of the neural network layers is a conditional neural network layer. Processing a layer input using a conditional neural network layer to generate a layer output includes obtaining values of one or more decision parameters of the conditional neural network layer. The neural network processes the layer input and the decision parameters of the conditional neural network layer to determine values of one or more latent parameters of the conditional neural network layer from a continuous set of possible latent parameter values. The values of the latent parameters specify the values of the conditional layer weights.