公开(公告)号：US20230064328A1

公开(公告)日：2023-03-02

申请号：US17459964

申请日：2021-08-27

Applicant: Google LLC

Inventor： Colvin Pitts ,  Yukun Zhu ,  Xuhui Jia

IPC: H04L29/06 ,  G06K9/00 ,  G06T11/00 ,  H04N5/272

Abstract: A computing system and method that can be used for safe and privacy preserving video representations of participants in a videoconference. In particular, the present disclosure provides a general pipeline for generating reconstructions of videoconference participants based on semantic statuses and/or activity statuses of the participants. The systems and methods of the present disclosure allow for videoconferences that convey necessary or meaningful information of participants through presentation of generalized representations of participants while filtering unnecessary or unwanted information from the representations by leveraging machine-learning models.

公开(公告)号：US10154197B2

公开(公告)日：2018-12-11

申请号：US15203643

申请日：2016-07-06

Applicant: Google LLC

Inventor： Jerome Chandra Bhat ,  Brandon Elliott Merle Clarke ,  Graham Butler Myhre ,  Ravi Kiran Nalla ,  Steven David Oliver ,  Tony Yip Pang Poon ,  William D. Houck, II ,  Colvin Pitts ,  Yi-Ren Ng ,  Kurt Akeley

IPC: H04N7/18 ,  G02B7/02 ,  H04N5/232 ,  H04N5/225 ,  G02F1/1337 ,  H04N13/289 ,  G02B27/00 ,  G02B7/08 ,  G02B3/12 ,  H04N13/232 ,  H04N13/296

Abstract: An image capture device, such as a camera, has multiple modes including a light field image capture mode, a conventional 2D image capture mode, and at least one intermediate image capture mode. By changing position and/or properties of the microlens array (MLA) in front of the image sensor, changes in 2D spatial resolution and angular resolution can be attained. In at least one embodiment, such changes can be performed in a continuous manner, allowing a continuum of intermediate modes to be attained.