公开(公告)号：US20180160106A1

公开(公告)日：2018-06-07

申请号：US15843366

申请日：2017-12-15

Applicant: GOOGLE LLC

Inventor： Carlos Hernandez Esteban ,  Robert Anderson ,  Changchang Wu ,  Michael Krainin

IPC: G02B27/01 ,  G06T15/20

CPC classification number: H04N13/344 ,  G02B27/017 ,  G02B27/0172 ,  G02B2027/011 ,  G02B2027/0134 ,  G02B2027/0138 ,  G02B2027/014 ,  G02B2027/0187 ,  G06T15/205 ,  H04N13/111 ,  H04N13/161 ,  H04N13/211 ,  H04N13/221 ,  H04N13/239 ,  H04N13/243 ,  H04N13/296 ,  H04N13/366

Abstract: Systems and methods are described include defining, at a computing device, a set of images based on captured images, projecting, at the computing device, a portion of the set of images from a planar perspective image plane onto a spherical image plane by recasting a plurality of viewing rays associated with the portion of the set of images from a plurality of viewpoints arranged around a curved path to a viewpoint, determining, at the computing device, a periphery boundary corresponding to the viewpoint and generating updated images by removing pixels that are outside of the periphery boundary, and providing, for display, the updated images within the bounds of the periphery boundary.

公开(公告)号：US10375381B2

公开(公告)日：2019-08-06

申请号：US15843366

申请日：2017-12-15

Applicant: GOOGLE LLC

Inventor： Carlos Hernandez Esteban ,  Robert Anderson ,  Changchang Wu ,  Michael Krainin

IPC: H04N13/243 ,  H04N13/344 ,  G02B27/01 ,  H04N13/366 ,  G06T15/20 ,  H04N13/211 ,  H04N13/221 ,  H04N13/111 ,  H04N13/161 ,  H04N13/296 ,  H04N13/239

Abstract: Systems and methods are described include defining, at a computing device, a set of images based on captured images, projecting, at the computing device, a portion of the set of images from a planar perspective image plane onto a spherical image plane by recasting a plurality of viewing rays associated with the portion of the set of images from a plurality of viewpoints arranged around a curved path to a viewpoint, determining, at the computing device, a periphery boundary corresponding to the viewpoint and generating updated images by removing pixels that are outside of the periphery boundary, and providing, for display, the updated images within the bounds of the periphery boundary.

公开(公告)号：US11483463B2

公开(公告)日：2022-10-25

申请号：US16883587

申请日：2020-05-26

Applicant: Google LLC

Inventor： Julia Winn ,  Abraham Stephens ,  Daniel Pettigrew ,  Aaron Maschinot ,  Ce Liu ,  Michael Krainin ,  Michael Rubinstein ,  Jingyu Cui

IPC: G06K9/34 ,  H04N5/232 ,  B60J3/04 ,  G02F1/1333 ,  G02F1/137 ,  H04N5/00 ,  H04N1/60 ,  G06T5/00 ,  H04N1/38 ,  G06T5/50 ,  H05B45/20

Abstract: Some implementations relate to determining whether glare is present in captured image(s) of an object (e.g., a photo) and/or to determining one or more attributes of any present glare. Some of those implementations further relate to adapting one or more parameters for a glare removal process based on whether the glare is determined to be present and/or based on one or more of the determined attributes of any glare determined to be present. Some additional and/or alternative implementations disclosed herein relate to correcting color of a flash image of an object (e.g., a photo). The flash image is based on one or more images captured by a camera of a client device with a flash component of the client device activated. In various implementations, correcting the color of the flash image is based on a determined color space of an ambient image of the object.

公开(公告)号：US12260572B2

公开(公告)日：2025-03-25

申请号：US17907529

申请日：2021-08-05

Applicant: Google LLC

Inventor： Varun Jampani ,  Huiwen Chang ,  Kyle Sargent ,  Abhishek Kar ,  Richard Tucker ,  Dominik Kaeser ,  Brian L. Curless ,  David Salesin ,  William T. Freeman ,  Michael Krainin ,  Ce Liu

IPC: G06T7/00 ,  G06T5/60 ,  G06T5/77 ,  G06T7/50

Abstract: A method includes determining, based on an image having an initial viewpoint, a depth image, and determining a foreground visibility map including visibility values that are inversely proportional to a depth gradient of the depth image. The method also includes determining, based on the depth image, a background disocclusion mask indicating a likelihood that pixel of the image will be disoccluded by a viewpoint adjustment. The method additionally includes generating, based on the image, the depth image, and the background disocclusion mask, an inpainted image and an inpainted depth image. The method further includes generating, based on the depth image and the inpainted depth image, respectively, a first three-dimensional (3D) representation of the image and a second 3D representation of the inpainted image, and generating a modified image having an adjusted viewpoint by combining the first and second 3D representation based on the foreground visibility map.

公开(公告)号：US20240249422A1

公开(公告)日：2024-07-25

申请号：US17907529

申请日：2021-08-05

Applicant: Google LLC

Inventor： Varun Jampani ,  Huiwen Chang ,  Kyle Sargent ,  Abhishek Kar ,  Richard Tucker ,  Dominik Kaeser ,  Brian L. Curless ,  David Salesin ,  William T. Freeman ,  Michael Krainin ,  Ce Liu

IPC: G06T7/50 ,  G06T5/60 ,  G06T5/77

CPC classification number: G06T7/50 ,  G06T5/60 ,  G06T5/77 ,  G06T2207/20081

Abstract: A method includes determining, based on an image having an initial viewpoint, a depth image, and determining a foreground visibility map including visibility values that are inversely proportional to a depth gradient of the depth image. The method also includes determining, based on the depth image, a background disocclusion mask indicating a likelihood that pixel of the image will be disoccluded by a viewpoint adjustment. The method additionally includes generating, based on the image, the depth image, and the background disocclusion mask, an inpainted image and an inpainted depth image. The method further includes generating, based on the depth image and the inpainted depth image, respectively, a first three-dimensional (3D) representation of the image and a second 3D representation of the inpainted image, and generating a modified image having an adjusted viewpoint by combining the first and second 3D representation based on the foreground visibility map.

公开(公告)号：US10675955B2

公开(公告)日：2020-06-09

申请号：US15812622

申请日：2017-11-14

Applicant: Google LLC

Inventor： Julia Winn ,  Abraham Stephens ,  Daniel Pettigrew ,  Aaron Maschinot ,  Ce Liu ,  Michael Krainin ,  Michael Rubinstein ,  Jingyu Cui

IPC: G06K9/34 ,  B60J3/04 ,  G02F1/1333 ,  G02F1/137 ,  H04N5/00 ,  H04N1/60 ,  G06T5/00 ,  H04N1/38 ,  H04N5/232 ,  G06T5/50 ,  H05B45/20

Abstract: Some implementations relate to determining whether glare is present in captured image(s) of an object (e.g., a photo) and/or to determining one or more attributes of any present glare. Some of those implementations further relate to adapting one or more parameters for a glare removal process based on whether the glare is determined to be present and/or based on one or more of the determined attributes of any glare determined to be present. Some additional and/or alternative implementations disclosed herein relate to correcting color of a flash image of an object (e.g., a photo). The flash image is based on one or more images captured by a camera of a client device with a flash component of the client device activated. In various implementations, correcting the color of the flash image is based on a determined color space of an ambient image of the object.