-
公开(公告)号：US11277583B2
公开(公告)日：2022-03-15
申请号：US17114852
申请日：2020-12-08
Applicant: Google LLC
Inventor： Colvin Pitts
IPC: G06N20/00 , G11B27/034 , G11B27/34 , H04N7/01 , G06K9/00
Abstract: Described are methods, systems, and computer-readable media to automatically crop videos using personalized parameters. Some implementations include a computer-implemented method that comprises obtaining an input video, determining a per-frame crop score for one or more candidate crop regions in each frame of the input video, generating a face signal for the one or more candidate crop regions, adjusting each per-frame crop score based on the face signal, determining a minimal cost path that represents crop region locations based on motion cost and the adjusted per-frame crop score, generating crop keyframing corresponding to the crop region locations along the minimal cost path, wherein the crop keyframing includes a start frame, an end frame, and crop region location, and outputting a modified video that has one or more of an output aspect ratio or an output orientation that is different than a corresponding aspect ratio or an orientation of the input video.
-
公开(公告)号：US10951880B2
公开(公告)日：2021-03-16
申请号：US16520961
申请日：2019-07-24
Applicant: GOOGLE LLC
Inventor： Colvin Pitts
IPC: H04N13/282 , H04N13/111 , H04N13/243 , H04N13/275 , H04N13/388 , H04N13/117 , H04N13/232 , H04N13/25 , G06T15/20 , H04N5/225 , H04N13/344
Abstract: A light-field camera system such as a tiled camera array may be used to capture a light-field of an environment. The tiled camera array may be a tiered camera array with a first plurality of cameras and a second plurality of cameras that are arranged more densely, but have lower resolution, than those of the first plurality of cameras. The first plurality of cameras may be interspersed among the second plurality of cameras. The first and second pluralities may cooperate to capture the light-field. According to one method, a subview may be captured by each camera of the first and second pluralities. Estimated world properties of the environment may be computed for each subview. A confidence map may be generated to indicate a level of confidence in the estimated world properties for each subview. The confidence maps and subviews may be used to generate a virtual view of the environment.
-
公开(公告)号：US10567464B2
公开(公告)日：2020-02-18
申请号：US15832023
申请日：2017-12-05
Applicant: Google LLC
Inventor： Derek Pang , Colvin Pitts , Kurt Akeley
IPC: H04L29/06 , H04N19/124 , H04N19/44 , H04N19/196 , H04N19/13 , H04N5/247 , H04N13/156 , H04N5/225 , H04N13/243 , H04N5/222 , H04N13/194 , H04N13/117 , H04N19/176 , H04N19/33 , H04N13/161 , H04N13/282 , H04N13/232 , H04N19/103 , H04N19/147 , H04N19/46 , H04N19/86 , H04N19/597 , H04N13/349 , H04N19/553 , H04N13/275 , H04N21/81 , H04N13/344 , H04N19/436
Abstract: A video stream of a scene for a virtual reality or augmented reality experience may be captured by one or more image capture devices. Data from the video stream may be retrieved, including base vantage data with base vantage color data depicting the scene from a base vantage location, and target vantage data with target vantage color data depicting the scene from a target vantage location. The base vantage data may be reprojected to the target vantage location to obtain reprojected target vantage data. The reprojected target vantage data may be compared with the target vantage data to obtain residual data. The residual data may be compressed by removing a subset of the residual data that is likely to be less viewer-discernable than a remainder of the residual data. A compressed video stream may be stored, including the base vantage data and the compressed residual data.
-
公开(公告)号：US10469873B2
公开(公告)日：2019-11-05
申请号：US15730096
申请日：2017-10-11
Applicant: Google LLC
Inventor： Derek Pang , Colvin Pitts , Kurt Akeley , Zeyar Htet
IPC: H04N19/597 , H04N19/44 , H04N19/162 , H04N19/436 , H04N19/186 , H04N19/176 , H04N5/222 , H04N5/225 , H04N5/247 , H04N13/243 , H04N13/194 , H04N13/232 , H04N13/282 , H04N13/156 , H04N13/117 , H04N13/161 , H04N19/93 , H04N19/91 , H04N13/366 , H04N13/344 , H04N13/275
Abstract: A virtual reality or augmented reality experience of a scene may be decoded for playback for a viewer through a combination of CPU and GPU processing. A video stream may be retrieved from a data store. A first viewer position and/or orientation may be received from an input device, such as the sensor package on a head-mounted display (HMD). At a processor, the video stream may be partially decoded to generate a partially-decoded bitstream. At a graphics processor, the partially-decoded bitstream may be further decoded to generate viewpoint video of the scene from a first virtual viewpoint corresponding to the first viewer position and/or orientation. The viewpoint video may be displayed on a display device, such as screen of the HMD.
-
公开(公告)号：US10275898B1
公开(公告)日：2019-04-30
申请号：US15590951
申请日：2017-05-09
Applicant: Google LLC
Inventor： Alex Song , Jonathan Frank , Julio C. Hernandez Zaragoza , Orin Green , Steve Cooper , Ariel Braunstein , Tim Milliron , Colvin Pitts , Yusuke Yasui , Saeid Shahhosseini , Bipeng Zhang
Abstract: A combined video of a scene may be generated for applications such as virtual reality or augmented reality. In one method, a camera system may be oriented at a first orientation and used to capture first video of a first portion of the scene. The camera system may then be rotated to a second orientation and used to capture second video of a second portion of the scene that is offset from the first portion such that the first video and the second video each have an overlapping video portion depicting an overlapping portion of the scene in which the first portion and the second portion of the scene overlap with each other. The first and second portions may be combined together to generate the combined video, which may depict the first and second portions substantially without duplicative inclusion of the overlapping video portion.
-
Patent Agency Ranking
公开(公告)号：US20240205278A1
公开(公告)日：2024-06-20
申请号：US18591787
申请日：2024-02-29
Applicant: Google LLC
Inventor： Colvin Pitts , Yukun Zu , Xuhui Jia
CPC classification number: H04L65/403 , G06T11/00 , G06V20/41 , G06V40/20 , H04L63/105 , 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：US11949724B2
公开(公告)日：2024-04-02
申请号：US17459964
申请日：2021-08-27
Applicant: Google LLC
Inventor： Colvin Pitts , Yukun Zhu , Xuhui Jia
CPC classification number: H04L65/403 , G06T11/00 , G06V20/41 , G06V40/20 , H04L63/105 , 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：US11641445B2
公开(公告)日：2023-05-02
申请号：US17665748
申请日：2022-02-07
Applicant: Google LLC
Inventor： Colvin Pitts
Abstract: Described are methods, systems, and computer-readable media to automatically crop videos using personalized parameters. Some implementations include a computer-implemented method that comprises obtaining an input video, determining a per-frame crop score for one or more candidate crop regions in each frame of the input video, generating a face signal for the one or more candidate crop regions, adjusting each per-frame crop score based on the face signal, determining a minimal cost path that represents crop region locations based on motion cost and the adjusted per-frame crop score, generating crop keyframing corresponding to the crop region locations along the minimal cost path, wherein the crop keyframing includes a start frame, an end frame, and crop region location, and outputting a modified video that has one or more of an output aspect ratio or an output orientation that is different than a corresponding aspect ratio or an orientation of the input video.
-
公开(公告)号：US20230045116A1
公开(公告)日：2023-02-09
申请号：US17394321
申请日：2021-08-04
Applicant: Google LLC
Inventor： Colvin Pitts , Aaron Michael Donsbach
Abstract: Systems and methods for multi-attendee video conferencing are described. A system can convert from huddle video conference mode to spatial video conference mode. In particular, by assigning user roles, specific users can have greater control of the video conference as compared to other users. For instance, moderators may have a greater level of control of the video conferencing system. Thus, in example implementations of the present disclosure, specific users can affect transition between two or more video conferencing modes, such as between a huddle video conference mode and a spatial video conference mode.
-
公开(公告)号：US20210185273A1
公开(公告)日：2021-06-17
申请号：US17114852
申请日：2020-12-08
Applicant: Google LLC
Inventor： Colvin Pitts
IPC: H04N7/01 , G06K9/00 , G06N20/00 , G11B27/34 , G11B27/034
Abstract: Described are methods, systems, and computer-readable media to automatically crop videos using personalized parameters. Some implementations include a computer-implemented method that comprises obtaining an input video, determining a per-frame crop score for one or more candidate crop regions in each frame of the input video, generating a face signal for the one or more candidate crop regions, adjusting each per-frame crop score based on the face signal, determining a minimal cost path that represents crop region locations based on motion cost and the adjusted per-frame crop score, generating crop keyframing corresponding to the crop region locations along the minimal cost path, wherein the crop keyframing includes a start frame, an end frame, and crop region location, and outputting a modified video that has one or more of an output aspect ratio or an output orientation that is different than a corresponding aspect ratio or an orientation of the input video.
-
-
-
-
-
-
-
-
-
Search Results
22
records
(took 0.025 seconds)
