公开(公告)号：US20240193895A1

公开(公告)日：2024-06-13

申请号：US18535051

申请日：2023-12-11

Applicant: GOOGLE LLC

Inventor： Jiayang Zhang ,  Daniel Edmond Fish ,  Eric Baczuk ,  Lynn Tsai

IPC: G06T19/20 ,  G06F3/01 ,  G06T13/40

CPC classification number: G06T19/20 ,  G06F3/013 ,  G06T13/40 ,  G06T2219/2016 ,  H04L65/403

Abstract: A method of facilitating a virtual conference includes determining that a first object is non-directional, the first object being presented within an original image on a first display within the virtual conference; based on determining that the first object is non-directional, reversing an appearance and a location of the first object to generate a reversed first object; determining that a second object is directional, the second object being presented within the original image on the first display within the virtual conference; based on determining that the second object is directional, transferring a location of the second object while maintaining an orientation of the second object to generate a transferred second object; and causing a second display to generate a transformed image, the transformed image including the reversed first object and the transferred second object.

公开(公告)号：US20220398705A1

公开(公告)日：2022-12-15

申请号：US17754392

申请日：2021-04-08

Applicant: GOOGLE LLC

Inventor： Ricardo Martin Brualla ,  Daniel Goldman ,  Hugues Herve Hoppe ,  Lynn Tsai ,  Lars Peter Johannes Hedman

IPC: G06T5/50 ,  G06T3/00 ,  G06T5/00 ,  G06T15/20 ,  G06T7/55

Abstract: Systems and methods are described for receiving a plurality of input images, a plurality of depth images, and a plurality of view parameters for generating a virtual view of a target subject. The systems and methods may generate a plurality of warped images based on the plurality of input images, the plurality of view parameters, and at least one of the plurality of depth images. In response to providing the plurality of depth images, the plurality of view parameters, and the plurality of warped images to a neural network, the systems and methods may receive, from the neural network, blending weights for assigning color to pixels of the virtual view of the target subject and may generate, based on the blending weights and the virtual view, a synthesized image according to the view parameters.