公开(公告)号：US12157051B2

公开(公告)日：2024-12-03

申请号：US17782460

申请日：2019-12-04

Applicant: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.

Inventor： Yow-Wei Cheng ,  Peter Christian Peterson ,  Kaden Strand

IPC: G02B27/01 ,  A61B5/00 ,  A63F13/212 ,  A63F13/77

Abstract: According to aspects of the present disclosure, there are provided methods and apparatus for providing a user characteristics determination module for use with a head-mountable display device, comprising: a biological characteristics handler to determine whether biological sensor data is indicative of a predefined biological characteristic of the user; and determination logic to determine and output a predefined response to the determined biological characteristic of the user.

公开(公告)号：US20240312095A1

公开(公告)日：2024-09-19

申请号：US18576628

申请日：2021-07-09

Applicant: Hewlett-Packard Development Company, L.P.

Inventor： Jishang Wei ,  Joseph Nouri ,  Kaden Strand ,  Rafael Ballagas

IPC: G06T13/40 ,  G06V10/44 ,  G06V40/16

CPC classification number: G06T13/40 ,  G06V10/44 ,  G06V40/174

Abstract: Avatar training images of facial avatars having facial expressions corresponding to specified blendshape weights are rendered. A two-stage machine learning model is trained based on the rendered avatar training images and the specified blendshape weights. The machine learning model has a first stage extracting image features from the rendered avatar training images and a second stage predicting blendshape weights from the extracted image features. The trained machine learning model is applied to predict the blendshape weights for a facial expression of a wearer of a head-mountable display (HMD) from a set of images captured by the HMD of a face of the wearer when exhibiting the facial expression.

公开(公告)号：US20240201733A1

公开(公告)日：2024-06-20

申请号：US18555667

申请日：2021-04-23

Applicant: Hewlett-Packard Development Company, L.P.

Inventor： Joseph Nouri ,  Kaden Strand

IPC: G06F1/14

CPC classification number: G06F1/14

Abstract: As sensor readings are received from a hardware sensor, each sensor reading is stored within a buffer along with a system timestamp of a system clock indicating when the sensor reading was received. Each sensor reading includes a sensor timestamp of a sensor clock indicating when the sensor reading occurred at the hardware sensor. Responsive to receipt of each sensor reading, a synthetic timestamp compensating for skew between the system clock and the sensor clock is generated and applied to the sensor reading. The synthetic timestamp is generated based on an average skew of the sensor readings within the buffer and an initial system timestamp indicating when a first sensor reading was received.