公开(公告)号：US10750210B2

公开(公告)日：2020-08-18

申请号：US16443481

申请日：2019-06-17

Applicant: Google LLC

Inventor： Daniel Goldman ,  Jason Lawrence ,  Andrew Huibers ,  Andrew Ian Russell ,  Steven M. Seitz

IPC: H04N21/222 ,  H04N7/15 ,  H04N21/2187 ,  H04N21/2343 ,  H04N21/242 ,  H04N21/4223 ,  H04N21/43 ,  H04N21/61 ,  H04N21/854 ,  H04N21/2365 ,  H04N21/239 ,  H04N21/431 ,  H04N13/305 ,  G02B27/01 ,  G02F1/29 ,  H04N7/14 ,  H04R1/02 ,  H04R3/00 ,  H04N21/41

Abstract: An example telepresence terminal includes a lenticular display, an image sensor, an infrared emitter, and an infrared depth sensor. The terminal may determine image data using visible light emitted by the infrared emitter and captured by the image sensor and determine depth data using infrared light captured by the infrared depth sensor. The terminal may also communicate the depth data and the image data to a remote telepresence terminal and receive remote image data and remote depth data. The terminal may also generate a first display image using the lenticular display based on the remote image data that is viewable from a first viewing location and generate a second display image using the lenticular display based on the remote image data and the remote depth data that is viewable from a second viewing location.

公开(公告)号：US20230319424A1

公开(公告)日：2023-10-05

申请号：US18246609

申请日：2021-11-09

Applicant: Google LLC

Inventor： Jason Lawrence ,  Supreeth Achar ,  Zhihao Xia

IPC: H04N23/84 ,  H04N23/11 ,  H04N23/56 ,  G06T5/00

CPC classification number: H04N23/84 ,  H04N23/11 ,  H04N23/56 ,  G06T5/002 ,  G06T2207/10024 ,  G06T2207/10048 ,  G06T2207/20084 ,  G06T2207/20081 ,  G06T2207/10012

Abstract: Techniques of estimating surface normals and reflectance from poorly-lit images includes using, in addition to an RGB image of a subject of a set of subjects, an image illuminated with near-infrared (NIR) radiation to determine albedo and surface normal maps for performing an image relighting, the image being captured with the NIR radiation from essentially the same perspective from which the RGB image was captured. In some implementations, a prediction engine takes as input a single RGB image and a single NIR image and estimates surface normals and reflectance from the subject.

公开(公告)号：US20230316810A1

公开(公告)日：2023-10-05

申请号：US18246625

申请日：2020-11-30

Applicant: Google LLC

Inventor： Sascha Haeberling ,  Jason Lawrence

IPC: G06V40/16 ,  G06T15/00 ,  G06V10/30

CPC classification number: G06V40/174 ,  G06T15/00 ,  G06V10/30 ,  G06V40/171 ,  G06V2201/07

Abstract: A method including capturing at least one image using a plurality of cameras, identifying a plurality of facial features associated with the at least one image, stabilizing a location of at least one facial feature of the plurality of facial features, converting the location of the at least one facial feature to a three-dimensional (3D) location, predicting a future location of the at least one facial feature, and rendering a 3D image, on a flat panel display, using the future location of the at least one facial feature.

公开(公告)号：US20230088801A1

公开(公告)日：2023-03-23

申请号：US17754626

申请日：2021-04-08

Applicant: GOOGLE LLC

Inventor： Jason Lawrence ,  Supreeth Achar ,  Zhihao Xia

IPC: H04N23/72 ,  H04N23/74 ,  H04N23/76 ,  H04N9/64 ,  G06T5/50

Abstract: An imaging system includes a processor, a memory, a visible light camera configured to record a first image of a scene, and an infrared camera configured to record a second image of the scene. The processor configured to execute instructions stored in the memory to input the first image and the second image into a neural network. The neural network relights the first image, based on characteristics of the second image, to correspond to an image of the scene under canonical illumination conditions.

公开(公告)号：US20200344500A1

公开(公告)日：2020-10-29

申请号：US16946826

申请日：2020-07-08

Applicant: Google LLC

Inventor： Daniel Goldman ,  Jason Lawrence ,  Andrew Huibers ,  Andrew Ian Russell ,  Steven M. Seitz

IPC: H04N21/222 ,  H04N7/15 ,  H04N21/2187 ,  H04N21/2343 ,  H04N21/242 ,  H04N21/4223 ,  H04N21/43 ,  H04N21/61 ,  H04N21/854 ,  H04N21/2365 ,  H04N21/239 ,  H04N21/431 ,  H04N13/305 ,  G02B27/01 ,  G02F1/29 ,  H04N7/14 ,  H04R1/02 ,  H04R3/00

Abstract: An example telepresence terminal includes a display, an image sensor, an infrared emitter, and an infrared depth sensor. The terminal may determine image data using visible light emitted by the infrared emitter and captured by the image sensor and determine depth data using infrared light captured by the infrared depth sensor. The terminal may also communicate the depth data and the image data to a remote telepresence terminal and receive remote image data and remote depth data. The terminal may also generate a first display image using the lenticular display based on the remote image data that is viewable from a first viewing location and generate a second display image using the lenticular display based on the remote image data and the remote depth data that is viewable from a second viewing location.

公开(公告)号：US20190306541A1

公开(公告)日：2019-10-03

申请号：US16443481

申请日：2019-06-17

Applicant: Google LLC

Inventor： Daniel Goldman ,  Jason Lawrence ,  Andrew Huibers ,  Andrew Ian Russell ,  Steven M. Seitz

IPC: H04N21/222 ,  H04N7/15 ,  H04N21/2187 ,  G02B27/01 ,  H04N7/14 ,  H04N21/61 ,  H04N21/43 ,  H04N21/4223 ,  H04N21/242 ,  G02F1/29 ,  H04R1/02 ,  H04R3/00 ,  H04N13/305 ,  H04N21/431 ,  H04N21/239 ,  H04N21/2365 ,  H04N21/854 ,  H04N21/2343

Abstract: An example telepresence terminal includes a lenticular display, an image sensor, an infrared emitter, and an infrared depth sensor. The terminal may determine image data using visible light emitted by the infrared emitter and captured by the image sensor and determine depth data using infrared light captured by the infrared depth sensor. The terminal may also communicate the depth data and the image data to a remote telepresence terminal and receive remote image data and remote depth data. The terminal may also generate a first display image using the lenticular display based on the remote image data that is viewable from a first viewing location and generate a second display image using the lenticular display based on the remote image data and the remote depth data that is viewable from a second viewing location.

公开(公告)号：US10327014B2

公开(公告)日：2019-06-18

申请号：US15699651

申请日：2017-09-08

Applicant: Google LLC

Inventor： Daniel Goldman ,  Jason Lawrence ,  Andrew Huibers ,  Andrew Ian Russell ,  Steven M. Seitz

IPC: G02F1/29 ,  H04N7/14 ,  H04N7/15 ,  H04R1/02 ,  H04R3/00 ,  G02B27/01 ,  H04N21/41 ,  H04N21/43 ,  H04N21/61 ,  H04N13/305 ,  H04N21/222 ,  H04N21/239 ,  H04N21/242 ,  H04N21/431 ,  H04N21/854 ,  H04N21/2187 ,  H04N21/2343 ,  H04N21/2365 ,  H04N21/4223

Abstract: An example telepresence terminal includes a lenticular display, an image sensor, an infrared emitter, and an infrared depth sensor. The terminal may determine image data using visible light emitted by the infrared emitter and captured by the image sensor and determine depth data using infrared light captured by the infrared depth sensor. The terminal may also communicate the depth data and the image data to a remote telepresence terminal and receive remote image data and remote depth data. The terminal may also generate a first display image using the lenticular display based on the remote image data that is viewable from a first viewing location and generate a second display image using the lenticular display based on the remote image data and the remote depth data that is viewable from a second viewing location.