公开(公告)号：WO2013176894A2

公开(公告)日：2013-11-28

申请号：PCT/US2013/040240

申请日：2013-05-09

Applicant: GOOGLE INC.

Inventor： GALLUP, David ,  GOLOVINSKIY, Aleksy ,  LIN, Michael, Hongmai ,  REINHARDT, Tilman

IPC: G06K9/36

CPC classification number: G06T7/596 ,  G06T17/00

Abstract: In an embodiment, a method determines a three-dimensional model from a plurality of images taken of a geographic region by one or more cameras from different perspectives. The method includes determining, using a first stereo reconstruction technique: (i) a plurality of three- dimensional candidate surface points from the plurality of images, and (ii) which of the images in the plurality of images view each of the plurality of candidate surface points. The method also includes identifying an empty space between each of the plurality of candidate surface points and each camera model for the respective images determined to view the candidate surface point. The method further includes for each of a plurality of pairs of images from the plurality of images, determining, using a second stereo reconstruction technique, a surface estimate for the pair of images. The method also includes merging the surface estimates to identify a final surface.

Abstract translation: 在一个实施例中，一种方法从通过来自不同视角的一个或多个照相机拍摄的地理区域的多个图像确定三维模型。 该方法包括使用第一立体重建技术来确定：（i）来自多个图像的多个三维候选表面点，以及（ii）多个图像中的哪个图像查看多个候选中的每一个 表面点。 该方法还包括识别多个候选表面点中的每一个之间的空白空间以及确定为查看候选表面点的各个图像的每个相机模型。 该方法还包括用于来自多个图像的多对图像中的每一个，使用第二立体重建技术确定该对图像的表面估计。 该方法还包括合并表面估计以识别最终表面。

公开(公告)号：WO2016191708A1

公开(公告)日：2016-12-01

申请号：PCT/US2016/034711

申请日：2016-05-27

Applicant: GOOGLE INC.

Inventor： WEAVER, Joshua ,  ANDERSON, Robert ,  WU, Changchang ,  KRAININ, Michael ,  GALLUP, David ,  SEITZ, Steven Maxwell ,  ESTEBAN, Carlos Hernandez ,  VALENTE, Matthew Thomas ,  HOOVER, Christopher Edward ,  GOOSSENS, Erik Hubert Dolly

IPC: G03B17/56 ,  G03B37/04 ,  H04N5/225 ,  H04N5/232 ,  H04N13/02 ,  H04N13/04

CPC classification number: H04N13/243 ,  G03B17/561 ,  G03B37/04 ,  H04N5/2251 ,  H04N5/2258 ,  H04N5/23238 ,  H04N5/247 ,  H04N13/282 ,  H04N13/344

Abstract: Systems and methods are related to a camera rig and generating stereoscopic panoramas from captured images for display in a virtual reality (VR) environment.

Abstract translation: 系统和方法与相机钻机相关，并且从捕获的图像生成立体全景，以便在虚拟现实（VR）环境中显示。

公开(公告)号：WO2016191467A1

公开(公告)日：2016-12-01

申请号：PCT/US2016/034077

申请日：2016-05-25

Applicant: GOOGLE INC.

Inventor： GALLUP, David ,  ANDERSON, Robert ,  ESTEBAN, Carlos Hernandez ,  SEITZ, Steven Maxwell ,  ADAMS, Riley

IPC: H04N13/02 ,  H04N13/00 ,  H04N13/04

CPC classification number: G06T3/4038 ,  H04N13/106 ,  H04N13/239 ,  H04N13/243 ,  H04N13/344 ,  H04N13/366

Abstract: Systems and methods are described for defining a set of images based on captured images, receiving a viewing direction associated with a user of a virtual reality (VR) head mounted display, receiving an indication of a change in the viewing direction. The methods further include configuring, a re-projection of a portion of the set of images, the re-projection based at least in part on the changed viewing direction and a field of view associated with the captured images, and converting the portion from a spherical perspective projection into a planar perspective projection, rendering by the computing device and for display in the VR head mounted display, an updated view based on the re-projection, the updated view configured to correct distortion and provide stereo parallax in the portion, and providing, to the head mounted display, the updated view including a stereo panoramic scene corresponding to the changed viewing direction.

Abstract translation: 描述了基于捕获的图像来定义一组图像的系统和方法，接收与虚拟现实（VR）头戴式显示器的用户相关联的观看方向，接收观看方向的改变的指示。 所述方法还包括至少部分地基于所改变的观察方向和与所捕获图像相关联的视场来配置，所述图像集合的一部分的重新投影，所述重新投影将所述部分从 球面透视投影成平面透视投影，由计算设备呈现并用于显示在VR头戴式显示器中，基于重新投影的更新视图，配置为校正失真并在该部分中提供立体视差的更新视图，以及 向头戴式显示器提供包括与改变的观看方向对应的立体全景场景的更新视图。

公开(公告)号：WO2016154808A1

公开(公告)日：2016-10-06

申请号：PCT/CN2015/075241

申请日：2015-03-27

Applicant: GOOGLE INC. ,  ZHOU, Guiheng ,  CHEN, Liyong ,  LOU, Hui ,  KE, Junjie ,  CHEN, Hao ,  KONG, Deben ,  GALLUP, David

Inventor： ZHOU, Guiheng ,  CHEN, Liyong ,  LOU, Hui ,  KE, Junjie ,  CHEN, Hao ,  KONG, Deben ,  GALLUP, David

IPC: H04N5/225

CPC classification number: G06K9/00677 ,  G06F3/04815 ,  G06F3/0485 ,  G06K9/627 ,  G06K2009/2045

Abstract: The technology relates to navigating imagery that is organized into clusters based on common patterns exhibited when imagery is captured. For example, a set of captured images which satisfy a predetermined pattern may be determined. The images in the set of set of captured images may be grouped into one or more clusters according to the predetermined pattern. A request to display a first cluster of the one or more clusters may be received and, in response, a first captured image from the requested first cluster may be selected. The selected first captured image may then be displayed.

Abstract translation: 该技术涉及基于在捕获图像时展现的常见图案而被组织成群集的图像。 例如，可以确定满足预定图案的一组捕获图像。 捕获图像集合中的图像可以根据预定图案被分组成一个或多个聚类。 可以接收到显示一个或多个群集的第一群集的请求，并且作为响应，可以选择来自所请求的第一群集的第一捕获图像。 然后可以显示所选择的第一拍摄图像。

公开(公告)号：EP2856431A2

公开(公告)日：2015-04-08

申请号：EP13794453.4

申请日：2013-05-09

Applicant: Google Inc.

Inventor： GALLUP, David ,  GOLOVINSKIY, Aleksy ,  LIN, Michael, Hongmai ,  REINHARDT, Tilman

IPC: G06T15/00

CPC classification number: G06T7/596 ,  G06T17/00

Abstract: In an embodiment, a method determines a three-dimensional model from a plurality of images taken of a geographic region by one or more cameras from different perspectives. The method includes determining, using a first stereo reconstruction technique: (i) a plurality of three- dimensional candidate surface points from the plurality of images, and (ii) which of the images in the plurality of images view each of the plurality of candidate surface points. The method also includes identifying an empty space between each of the plurality of candidate surface points and each camera model for the respective images determined to view the candidate surface point. The method further includes for each of a plurality of pairs of images from the plurality of images, determining, using a second stereo reconstruction technique, a surface estimate for the pair of images. The method also includes merging the surface estimates to identify a final surface.

Abstract translation: ，实施例在确定性地雷从由一个或多个相机从不同的角度拍摄的地理区域的图像的多个A三维模型的方法。 该方法包括：确定数据挖掘，使用第一立体声重构技术：（ⅰ）三维候补表面点从图像中的多个A多个，并且（II）其中在图像的多个图像的查看每个候选的多个 表面点。 因此，该方法包括识别每一候选表面点的多元性和用于respectivement图像中的每个摄像机模型之间的空的空间的确定性开采，以查看所述候选表面点。 该方法包括进一步的每个对从图像，确定性挖掘的多个图像的多个，使用第二立体声重建技术，表面估计用于对图像。 因此，该方法包括：合并所述表面估计，以确定最终表面。