-
公开(公告)号：US20240395035A1
公开(公告)日：2024-11-28
申请号：US18790932
申请日：2024-07-31
Applicant: Google LLC
Inventor： Ryan Geiss , Ruido Yang , Marc Levoy
Abstract: Apparatus and methods related to photography are provided. A computing device can receive an input image. An object detector of the computing device can determine an object region of interest of the input image that is associated with an object detected in the input image. A trained machine learning algorithm can determine an output photographic region of interest for the input image based on the object region of interest and the input image. The machine learning algorithm can be trained to identify an output photographic region of interest that is suitable for use by a photographic function for image generation. The computing device can generate an output related to the output photographic region of interest.
-
公开(公告)号：US12056925B2
公开(公告)日：2024-08-06
申请号：US17299188
申请日：2019-01-15
Applicant: Google LLC
Inventor： Ryan Geiss , Ruiduo Yang , Marc Levoy
CPC classification number: G06V20/35 , G06N20/00 , G06V10/56 , H04N23/80 , G06T2207/20081 , G06T2207/20084
Abstract: Apparatus and methods related to photography are provided. A computing device can receive an input image. An object detector of the computing device can determine an object region of interest of the input image that is associated with an object detected in the input image. A trained machine learning algorithm can determine an output photographic region of interest for the input image based on the object region of interest and the input image. The machine learning algorithm can be trained to identify an output photographic region of interest that is suitable for use by a photographic function for image generation. The computing device can generate an output related to the output photographic region of interest.
-
公开(公告)号：US10187628B2
公开(公告)日：2019-01-22
申请号：US15676145
申请日：2017-08-14
Applicant: Google LLC
Inventor： Jonathan Tilton Barron , Stephen Joseph DiVerdi , Ryan Geiss
IPC: H04N13/239 , G06T7/38 , G06K9/62 , G06T5/00 , G06T5/10 , H04N9/09 , G06T7/269 , H04N5/235 , G06T7/292 , G06T7/30 , H04N13/271 , H04N13/00
Abstract: The present disclosure relates to methods and systems that may improve and/or modify images captured using multiscopic image capture systems. In an example embodiment, burst image data is captured via a multiscopic image capture system. The burst image data may include at least one image pair. The at least one image pair is aligned based on at least one rectifying homography function. The at least one aligned image pair is warped based on a stereo disparity between the respective images of the image pair. The warped and aligned images are then stacked and a denoising algorithm is applied. Optionally, a high dynamic range algorithm may be applied to at least one output image of the aligned, warped, and denoised images.
-
公开(公告)号：US09918065B2
公开(公告)日：2018-03-13
申请号：US15390016
申请日：2016-12-23
Applicant: Google LLC
Inventor： Ryan Geiss , Roman Lewkow
CPC classification number: H04N13/128 , H04N5/2258 , H04N5/23212 , H04N5/235 , H04N13/207 , H04N13/239 , H04N13/243 , H04N13/296
Abstract: Example embodiments may help multi-camera devices determine disparity information scene, and use the disparity information in an autofocus process. An example method involves: (a) receiving image data of a scene that comprises at least one image of the scene captured by each of two or more image-capture systems of a computing device that includes a plurality of image-capture systems; (b) using the image data captured by the two or more image-capture systems as a basis for determining disparity information for the scene; and (c) performing, by the computing system, an autofocus process based at least in part on the disparity information, wherein the autofocus process provides a focus setting for at least one of the image-capture systems of the computing device.
-
公开(公告)号：US20190124319A1
公开(公告)日：2019-04-25
申请号：US16226643
申请日：2018-12-20
Applicant: Google LLC
Inventor： Jonathan Tilton Barron , Stephen Joseph DiVerdi , Ryan Geiss
IPC: H04N13/239 , G06K9/62 , H04N5/235 , G06T5/00 , G06T5/10 , G06T7/269 , H04N13/271 , H04N9/09 , G06T7/38 , G06T7/30 , G06T7/292
Abstract: The present disclosure relates to methods and systems that may improve and/or modify images captured using multiscopic image capture systems. In an example embodiment, burst image data is captured via a multiscopic image capture system. The burst image data may include at least one image pair. The at least one image pair is aligned based on at least one rectifying homography function. The at least one aligned image pair is warped based on a stereo disparity between the respective images of the image pair. The warped and aligned images are then stacked and a denoising algorithm is applied. Optionally, a high dynamic range algorithm may be applied to at least one output image of the aligned, warped, and denoised images.
-
Patent Agency Ranking
公开(公告)号：USD985011S1
公开(公告)日：2023-05-02
申请号：US29709053
申请日：2019-10-10
Applicant: Google LLC
Designer： Michelle Chen , Ryan Geiss , Marc Levoy , Kelly Tsai , Chorong Johnston , Alexander Schiffhauer , Samuel Hasinoff
-
公开(公告)号：US20200084429A1
公开(公告)日：2020-03-12
申请号：US16680474
申请日：2019-11-11
Applicant: Google LLC
Inventor： Jonathan Tilton Barron , Stephen Joseph DiVerdi , Ryan Geiss
IPC: H04N13/239 , G06T7/292 , G06T7/269 , H04N9/09 , G06T5/10 , G06T5/00 , G06K9/62 , H04N13/271 , G06T7/30 , H04N5/235 , G06T7/38 , H04N13/25
Abstract: The present disclosure relates to methods and systems that may improve and/or modify images captured using multiscopic image capture systems. In an example embodiment, burst image data is captured via a multiscopic image capture system. The burst image data may include at least one image pair. The at least one image pair is aligned based on at least one rectifying homography function. The at least one aligned image pair is warped based on a stereo disparity between the respective images of the image pair. The warped and aligned images are then stacked and a denoising algorithm is applied. Optionally, a high dynamic range algorithm may be applied to at least one output image of the aligned, warped, and denoised images.
-
公开(公告)号：US10477185B2
公开(公告)日：2019-11-12
申请号：US16226643
申请日：2018-12-20
Applicant: Google LLC
Inventor： Jonathan Tilton Barron , Stephen Joseph DiVerdi , Ryan Geiss
IPC: H04N13/239 , G06T7/38 , G06K9/62 , G06T5/00 , G06T5/10 , H04N9/09 , G06T7/269 , H04N5/235 , G06T7/292 , G06T7/30 , H04N13/271 , H04N13/25 , H04N13/00
Abstract: The present disclosure relates to methods and systems that may improve and/or modify images captured using multiscopic image capture systems. In an example embodiment, burst image data is captured via a multiscopic image capture system. The burst image data may include at least one image pair. The at least one image pair is aligned based on at least one rectifying homography function. The at least one aligned image pair is warped based on a stereo disparity between the respective images of the image pair. The warped and aligned images are then stacked and a denoising algorithm is applied. Optionally, a high dynamic range algorithm may be applied to at least one output image of the aligned, warped, and denoised images.
-
公开(公告)号：US10330940B1
公开(公告)日：2019-06-25
申请号：US15450864
申请日：2017-03-06
Applicant: Google LLC
Inventor： Hayes Solos Raffle , Adrian Wong , Ryan Geiss
IPC: G02B27/01 , G06F3/01 , G09G5/00 , G02B27/00 , G06F3/0481
Abstract: Methods and systems involving a graphic display in a head mounted display (HMD) are disclosed herein. An exemplary system may be configured to: (1) at a computing system associated with a head-mountable display, receive head-movement data indicative of head movement; (2) use one or more context signals to determine a first activity associated with the head-mountable device; (3) determine a head-movement interpretation scheme corresponding to the first activity; (4) apply the determined head-movement interpretation scheme to determine input data corresponding to the received head-movement data; and (5) provide the determined input data for at least one function of the head-mountable display.
-
公开(公告)号：US20220076018A1
公开(公告)日：2022-03-10
申请号：US17299188
申请日：2019-01-15
Applicant: Google LLC
Inventor： Ryan Geiss , Ruiduo Yang , Marc Levoy
Abstract: Apparatus and methods related to photography are provided. A computing device can receive an input image. An object detector of the computing device can determine an object region of interest of the input image that is associated with an object detected in the input image. A trained machine learning algorithm can determine an output photographic region of interest for the input image based on the object region of interest and the input image. The machine learning algorithm can be trained to identify an output photographic region of interest that is suitable for use by a photographic function for image generation. The computing device can generate an output related to the output photographic region of interest.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.022 seconds)
